diff --git a/.gitattributes b/.gitattributes index 40e7a57a301a1184e9f40b0df319ea1aef1c46c2..393f9152e0b1867f0a6dd524cde968f91c6289f7 100644 --- a/.gitattributes +++ b/.gitattributes @@ -9165,3 +9165,258 @@ neuronxcc-2.17.194.0+d312836f/MODULE_14c06ce926029fd4a799+bfe5714b/model.neff fi neuronxcc-2.17.194.0+d312836f/MODULE_a1d0dc30908164d5670a+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_a1d0dc30908164d5670a+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_cf5f61d60b0a013ebeb0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4bd0c6ed2a9764168cb6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4bd0c6ed2a9764168cb6.json new file mode 100644 index 0000000000000000000000000000000000000000..7f7e7c4874088f7105a5a569dfc49a6e4a1e316b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4bd0c6ed2a9764168cb6.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/58bb3ae501d4d87ab565.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/58bb3ae501d4d87ab565.json new file mode 100644 index 0000000000000000000000000000000000000000..2734eb040650ae63e63fda14310a2ba2315b0dce --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/58bb3ae501d4d87ab565.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/f5771202abb1a7ae2611.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/f5771202abb1a7ae2611.json new file mode 100644 index 0000000000000000000000000000000000000000..6b23e1e35fa68cc54a8f4801c2011b0a3967402a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/f5771202abb1a7ae2611.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/ibm-granite/granite-3.1-2b-instruct/af1749224d7631fdb38a.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/ibm-granite/granite-3.1-2b-instruct/af1749224d7631fdb38a.json new file mode 100644 index 0000000000000000000000000000000000000000..5a66590f5dfe9a5c76806a8164b70fe1d7e72dbb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/granite/ibm-granite/granite-3.1-2b-instruct/af1749224d7631fdb38a.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/38357c754f2cbd1d382e.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/38357c754f2cbd1d382e.json new file mode 100644 index 0000000000000000000000000000000000000000..58da43d30f7e4c8421019dee35b1198e377eced2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/38357c754f2cbd1d382e.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 8, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "checkpoint_revision": "b1c0b44b4369b597ad119a196caf79a9c40e141e", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 24, + "logical_nc_config": 1, + "max_batch_size": 8, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 24, + "vocab_parallel": false + }, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/89acac1543511de63934.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/89acac1543511de63934.json new file mode 100644 index 0000000000000000000000000000000000000000..68ea8ffd46933ef1094de106382722c06e902017 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/89acac1543511de63934.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "checkpoint_revision": "b1c0b44b4369b597ad119a196caf79a9c40e141e", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 24, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 24, + "vocab_parallel": false + }, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/a91139c3aee28b0f6c94.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/a91139c3aee28b0f6c94.json new file mode 100644 index 0000000000000000000000000000000000000000..c3c030ce11fe934a47ac9b35e592c13020f8cb04 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/a91139c3aee28b0f6c94.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "checkpoint_revision": "b1c0b44b4369b597ad119a196caf79a9c40e141e", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 24, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 24, + "vocab_parallel": false + }, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/3ed9abae6f7f67d07da0.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/3ed9abae6f7f67d07da0.json new file mode 100644 index 0000000000000000000000000000000000000000..f686524a2d6a538c4f8d010f30213bd3861447f3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/3ed9abae6f7f67d07da0.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/42b299016a0208fd74b0.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/42b299016a0208fd74b0.json new file mode 100644 index 0000000000000000000000000000000000000000..ad9c014325f12bdfac6a43b874486321c9ee1c9d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/42b299016a0208fd74b0.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/7b749096ec9bec32a9c5.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/7b749096ec9bec32a9c5.json new file mode 100644 index 0000000000000000000000000000000000000000..96f145eb43d11982fba77a4981075582ec41fb36 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/7b749096ec9bec32a9c5.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 131072, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 131072, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 131072, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/c36bfaee43f6f840c055.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/c36bfaee43f6f840c055.json new file mode 100644 index 0000000000000000000000000000000000000000..f082ca228ebcd68110c3dd62b2d6c03556682de1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/c36bfaee43f6f840c055.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/29f3c7ef0e6a87f35788.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/29f3c7ef0e6a87f35788.json new file mode 100644 index 0000000000000000000000000000000000000000..f906b4847deeaa55f332d7cc289ff425109a9e0a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/29f3c7ef0e6a87f35788.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 48, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 48, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/6d3aa041c08b8396ee41.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/6d3aa041c08b8396ee41.json new file mode 100644 index 0000000000000000000000000000000000000000..3320bb51b7633791b098728cde07ea6abfe899e8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/6d3aa041c08b8396ee41.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 16, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 16, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7523661354aea5f66d6c.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7523661354aea5f66d6c.json new file mode 100644 index 0000000000000000000000000000000000000000..0690b8f1d1626134a6c57eb6f5f37ccb7620d0b3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7523661354aea5f66d6c.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7c2b4b0f296eeda524b6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7c2b4b0f296eeda524b6.json new file mode 100644 index 0000000000000000000000000000000000000000..86ca282d2159a873b578dbcbb1b6fd419f5e2b4b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/7c2b4b0f296eeda524b6.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/9932c1d05bd91a781c3a.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/9932c1d05bd91a781c3a.json new file mode 100644 index 0000000000000000000000000000000000000000..38e15bc6511de9330dbe671939236a99927cd1d2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/9932c1d05bd91a781c3a.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 8, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 8, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/ad521b5b119cf355612b.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/ad521b5b119cf355612b.json new file mode 100644 index 0000000000000000000000000000000000000000..bb118701c6ce26fdb8f2ee3223c204ebabba33c7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.1-8B-Instruct/ad521b5b119cf355612b.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.1-8B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 32, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.1-8B-Instruct", + "checkpoint_revision": "4699cc75b550f9c6f3173fb80f4703b62d946aa5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 32, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/6517315f1bb86d99f525.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/6517315f1bb86d99f525.json new file mode 100644 index 0000000000000000000000000000000000000000..b129be0d086baadb9b460890d6cb996117b0f53c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/6517315f1bb86d99f525.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ec762024d178ab5e922b.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ec762024d178ab5e922b.json new file mode 100644 index 0000000000000000000000000000000000000000..a340adf0eca90b295c1e8ca94b0a14da5216d19c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ec762024d178ab5e922b.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 5, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ee2a399906ca25519a40.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ee2a399906ca25519a40.json new file mode 100644 index 0000000000000000000000000000000000000000..cde00c7f90d0349725adc77211957349d85bfa79 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ee2a399906ca25519a40.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/350aa0c9a5de191ee7c7.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/350aa0c9a5de191ee7c7.json new file mode 100644 index 0000000000000000000000000000000000000000..5cbd62fac646f71d19cadd778e6448a358cce49d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/350aa0c9a5de191ee7c7.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/85ab3636ce10c112729d.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/85ab3636ce10c112729d.json new file mode 100644 index 0000000000000000000000000000000000000000..31e4625e2af61a82fa63c3d9079f7a0178659fdc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/85ab3636ce10c112729d.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/e6b337232e4796edc487.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/e6b337232e4796edc487.json new file mode 100644 index 0000000000000000000000000000000000000000..da83eb116375bf300e312fa4fbb5923e77a9beef --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/e6b337232e4796edc487.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/microsoft/Phi-3-mini-4k-instruct/aaf845721275df37b728.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/microsoft/Phi-3-mini-4k-instruct/aaf845721275df37b728.json new file mode 100644 index 0000000000000000000000000000000000000000..5afb9654e5afb765e67f9b6d30840a0429fd5084 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/microsoft/Phi-3-mini-4k-instruct/aaf845721275df37b728.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3-mini-4k-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" + }, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", + "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "sliding_window": 2047, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/16874c09c9bed580256d.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/16874c09c9bed580256d.json new file mode 100644 index 0000000000000000000000000000000000000000..bc5071c3ac3538b7f48eefd48e02e8796d89a7fa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/16874c09c9bed580256d.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/e38863225742ea4adc6d.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/e38863225742ea4adc6d.json new file mode 100644 index 0000000000000000000000000000000000000000..725ecb433acad65d2b2b0314fa07c9d12863d2c6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/e38863225742ea4adc6d.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/fecca0469b6993e5d3c5.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/fecca0469b6993e5d3c5.json new file mode 100644 index 0000000000000000000000000000000000000000..1bdd630cb1ea6a49fb173d05dbe028af004a5079 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/fecca0469b6993e5d3c5.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/373976326fffd2754567.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/373976326fffd2754567.json new file mode 100644 index 0000000000000000000000000000000000000000..6484e336784a544298607854d32c551236d98603 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/373976326fffd2754567.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/84548c49ed5ba851eeb3.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/84548c49ed5ba851eeb3.json new file mode 100644 index 0000000000000000000000000000000000000000..2754ed8fed8771f6d13a340485c4bf0f167e8f93 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/84548c49ed5ba851eeb3.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/92ed3c6dd358107ccc6f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/92ed3c6dd358107ccc6f.json new file mode 100644 index 0000000000000000000000000000000000000000..bb6d0a173d53af34da67f64e74b8836f2078d7c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/92ed3c6dd358107ccc6f.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 128, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 128, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 128, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/34b1d02021287cfd46b2.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/34b1d02021287cfd46b2.json new file mode 100644 index 0000000000000000000000000000000000000000..bc96f49a413219618e407ec2ac08fb468624ac79 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/34b1d02021287cfd46b2.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/7ee9b03bb7a8b01f359e.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/7ee9b03bb7a8b01f359e.json new file mode 100644 index 0000000000000000000000000000000000000000..f5b291ae9bd22dd367f855cfda07fc4fbbc08cc9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/7ee9b03bb7a8b01f359e.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/e709ce08492ca8a65007.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/e709ce08492ca8a65007.json new file mode 100644 index 0000000000000000000000000000000000000000..4072010b23b7d9e60055ac37011ec8d246b8f18d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/e709ce08492ca8a65007.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen3/Qwen/Qwen3-1.7B/4a3a9b902e21f2cd7582.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen3/Qwen/Qwen3-1.7B/4a3a9b902e21f2cd7582.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2815cede786bea20ae56c62ae928cc61ae1f43 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev2/qwen3/Qwen/Qwen3-1.7B/4a3a9b902e21f2cd7582.json @@ -0,0 +1,72 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-1.7B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen3-1.7B", + "checkpoint_revision": "0060bc56d46589041c1048efd1a397421b1142b5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/ibm-granite/granite-3.1-2b-instruct/2ccaa328023740986e21.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/ibm-granite/granite-3.1-2b-instruct/2ccaa328023740986e21.json new file mode 100644 index 0000000000000000000000000000000000000000..f21ca3bf07a515ee84cf73d6c06f0933148df39b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/ibm-granite/granite-3.1-2b-instruct/2ccaa328023740986e21.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.json new file mode 100644 index 0000000000000000000000000000000000000000..18e13ce6f21b86a92b96c1639f57d09f3550f95a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/microsoft/Phi-3-mini-4k-instruct/1e2d4e1d3b95dfb315e1.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/microsoft/Phi-3-mini-4k-instruct/1e2d4e1d3b95dfb315e1.json new file mode 100644 index 0000000000000000000000000000000000000000..ac98b70dda30cc4d2ce97af0eb07e8d709c1acb3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/microsoft/Phi-3-mini-4k-instruct/1e2d4e1d3b95dfb315e1.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3-mini-4k-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" + }, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", + "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "sliding_window": 2047, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/a40dd4e2c2b33ddea710.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/a40dd4e2c2b33ddea710.json new file mode 100644 index 0000000000000000000000000000000000000000..209da38ff239ada6d2148f22a0492b1ebd4c3b7f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/a40dd4e2c2b33ddea710.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen3/Qwen/Qwen3-0.6B/79fe6d5dc76e8ab41df4.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen3/Qwen/Qwen3-0.6B/79fe6d5dc76e8ab41df4.json new file mode 100644 index 0000000000000000000000000000000000000000..c0a3dce8eac5148671582c12b50774c1e0d86d9e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen3/Qwen/Qwen3-0.6B/79fe6d5dc76e8ab41df4.json @@ -0,0 +1,72 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "e6de91484c29aa9480d55605af694f39b081c455", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/81fac095f3d6ebe884c6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/81fac095f3d6ebe884c6.json new file mode 100644 index 0000000000000000000000000000000000000000..ee8ac2e5993245a71e71c4839d907a552732f59a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/81fac095f3d6ebe884c6.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c665cd695ad271120e6d.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c665cd695ad271120e6d.json new file mode 100644 index 0000000000000000000000000000000000000000..c0b6762ca6b916f0158d66de4fa3f8748d931e38 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c665cd695ad271120e6d.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ec221ea8393e9e9fd62f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ec221ea8393e9e9fd62f.json new file mode 100644 index 0000000000000000000000000000000000000000..1217ef9a3dad6b83f40fe3f1a0cd75950cee2c35 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ec221ea8393e9e9fd62f.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/ibm-granite/granite-3.1-2b-instruct/d891b7116252e4de6e44.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/ibm-granite/granite-3.1-2b-instruct/d891b7116252e4de6e44.json new file mode 100644 index 0000000000000000000000000000000000000000..76630adb803f25b10b5a91bdd4b95a7abd629777 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/granite/ibm-granite/granite-3.1-2b-instruct/d891b7116252e4de6e44.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/834a675df2e91e91bb4f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/834a675df2e91e91bb4f.json new file mode 100644 index 0000000000000000000000000000000000000000..699cf50a7129c38d5ad4789e074440c9517485f2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/834a675df2e91e91bb4f.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/836e81ae1c74a144e099.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/836e81ae1c74a144e099.json new file mode 100644 index 0000000000000000000000000000000000000000..73fa869cb02c66e0d2bfee9354dae11d445c210d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/836e81ae1c74a144e099.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/f070d170462fdefcc7cb.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/f070d170462fdefcc7cb.json new file mode 100644 index 0000000000000000000000000000000000000000..a738053bb07ab66d2698fe9aed3320930300c30f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/llamafactory/tiny-random-Llama-3/f070d170462fdefcc7cb.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/9e060dd6a7994acb47cf.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/9e060dd6a7994acb47cf.json new file mode 100644 index 0000000000000000000000000000000000000000..4f76a60583af05d31f482282b6c672ee18e01d4a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/9e060dd6a7994acb47cf.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/d8583f8c5b487ebc1043.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/d8583f8c5b487ebc1043.json new file mode 100644 index 0000000000000000000000000000000000000000..f55e4d3b085ded6512b7baab94fa01c3799ef7fb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/d8583f8c5b487ebc1043.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 5, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/ddc7f7d79500c5808b41.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/ddc7f7d79500c5808b41.json new file mode 100644 index 0000000000000000000000000000000000000000..f4fce67b58da2413831a6e11d954d1ebfdb4cca0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/ddc7f7d79500c5808b41.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/69a038e29d395e086427.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/69a038e29d395e086427.json new file mode 100644 index 0000000000000000000000000000000000000000..4d6b1c041faabd384ab45ea4abcb05f8a606f8f3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/69a038e29d395e086427.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/6fccf4132e08c10fb6ed.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/6fccf4132e08c10fb6ed.json new file mode 100644 index 0000000000000000000000000000000000000000..c2a91b13e4f6dec634497d7d2b5ea4c5c3745494 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/6fccf4132e08c10fb6ed.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/b5d0e0ab641066aac988.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/b5d0e0ab641066aac988.json new file mode 100644 index 0000000000000000000000000000000000000000..df316204c10e11d8d4f980431a06c28506c7ac37 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/mixtral/dacorvo/Mixtral-tiny/b5d0e0ab641066aac988.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/microsoft/Phi-3-mini-4k-instruct/615be44f3eba531309e1.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/microsoft/Phi-3-mini-4k-instruct/615be44f3eba531309e1.json new file mode 100644 index 0000000000000000000000000000000000000000..742b29d2f68790d0c89d2460c00da032404a9c6c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/microsoft/Phi-3-mini-4k-instruct/615be44f3eba531309e1.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3-mini-4k-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" + }, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", + "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "sliding_window": 2047, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/29065523ef8593d99a26.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/29065523ef8593d99a26.json new file mode 100644 index 0000000000000000000000000000000000000000..b00257f8bddaaea9465d6d1cfb550f5c2efef29b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/29065523ef8593d99a26.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/32d20ad3c3761878bac1.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/32d20ad3c3761878bac1.json new file mode 100644 index 0000000000000000000000000000000000000000..703efafa00a4165531fe1dee944262db9f76baf4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/32d20ad3c3761878bac1.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/491f4920beea5a951479.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/491f4920beea5a951479.json new file mode 100644 index 0000000000000000000000000000000000000000..fdc6b3d4da91a665fdf315ca2314787aabf4820a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/phi3/yujiepan/phi-4-tiny-random/491f4920beea5a951479.json @@ -0,0 +1,74 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ba36c59d51e312745276.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ba36c59d51e312745276.json new file mode 100644 index 0000000000000000000000000000000000000000..e9e67438468b4fa355786346c87f087e601c318c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ba36c59d51e312745276.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ef5175f619cf65f28451.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ef5175f619cf65f28451.json new file mode 100644 index 0000000000000000000000000000000000000000..ca0341992c98802a57f0d21a2b6ee934e21d8e6f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-0.5B/ef5175f619cf65f28451.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/31c678ff29ca005d73b6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/31c678ff29ca005d73b6.json new file mode 100644 index 0000000000000000000000000000000000000000..fac64f0efd158bd44cf378c5fab9fc942a1cd164 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/31c678ff29ca005d73b6.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-7B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-7B", + "checkpoint_revision": "d149729398750b98c0af14eb82c78cfe92750796", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 8, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 8, + "vocab_parallel": false + }, + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/e2252420d0e4c111b25f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/e2252420d0e4c111b25f.json new file mode 100644 index 0000000000000000000000000000000000000000..56014d675d5c719c496d90120f94795e92f70085 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/e2252420d0e4c111b25f.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-7B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-7B", + "checkpoint_revision": "d149729398750b98c0af14eb82c78cfe92750796", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/ee5dcec841d4170a5e77.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/ee5dcec841d4170a5e77.json new file mode 100644 index 0000000000000000000000000000000000000000..1bf3cee1d42f4e24b50a513017a2a443d541dab7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/ee5dcec841d4170a5e77.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-7B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-7B", + "checkpoint_revision": "d149729398750b98c0af14eb82c78cfe92750796", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/4ef1f3351a52ca03d475.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/4ef1f3351a52ca03d475.json new file mode 100644 index 0000000000000000000000000000000000000000..781ef6ac28a9a4b0c7a4592da474b1bed24b4ed8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/4ef1f3351a52ca03d475.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/b14391e61b47ceee3885.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/b14391e61b47ceee3885.json new file mode 100644 index 0000000000000000000000000000000000000000..0b5e2c25fd663c4dbc46ac108139f7d029a45129 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/b14391e61b47ceee3885.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e41fba961a8285bbb752.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e41fba961a8285bbb752.json new file mode 100644 index 0000000000000000000000000000000000000000..d442d1bf7f1648ed576eac44cc1c7930ff5efc87 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e41fba961a8285bbb752.json @@ -0,0 +1,75 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/5d5478ec2d2958693455.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/5d5478ec2d2958693455.json new file mode 100644 index 0000000000000000000000000000000000000000..608defb97b1090a3fac347f76c66f9c1709a9aec --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/5d5478ec2d2958693455.json @@ -0,0 +1,72 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "e6de91484c29aa9480d55605af694f39b081c455", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/bf62d8db5ea46ca61ae6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/bf62d8db5ea46ca61ae6.json new file mode 100644 index 0000000000000000000000000000000000000000..d5b9fb7516507bfda67fc144b25297fb1c048bfe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-0.6B/bf62d8db5ea46ca61ae6.json @@ -0,0 +1,72 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "e6de91484c29aa9480d55605af694f39b081c455", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4ef86bba6a55fe84f707cd4a7804eb1652e9888a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0586c9953cf96a4bf2dcd9f92fbeb91b5ee1d0c4a4fa4b6552ca650e05704245 +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a978b7c3d2899a1190213986ede5056215566c22 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ff2add9228e02876f3420c76e3459481645507f4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b6d089df781e3ab0dfe911812cbb200f2dc1d358cc2d49abd01f7222601b25 +size 497603 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..af08051da20c68315921439b2e9724d9fbe8630e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cdaa16cfce3a4b868994f3a379ad2cc60becae6b12accc37ba0c6e7b5b89ad +size 31345664 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5f147dd1be539b023212ad611bc29974c4c4e0fe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa1f1c8aa58964fa1c21d32c9f6b27235496ca5a3c5b0971eef05f395e17244 +size 374859 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..336a08de5bc102e1aafec6fa76ddc5657c0452a5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da21369640ee2df0dfcab62f75c2ce04e05c5f3599b229a1708a4f59645c5db4 +size 2151424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..65a9a9ee58130142902420ef2129c0a87d95fcf5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0173a1d42ddbeaeb8a09+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5826eda9203bc6afa922625653541f27e0e7117dd8fc9e58bf6ec170ee4c3ae5 +size 2221053 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cbff3da1a4453ede6bb6031b73f54e913150e13a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52c0497bb2f9417b413e7407edf5d7eaa44ba4fd866fea870205954a6bf774d +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..245ffce78607a2669e6c2cf8b4fdb5d9c85e3a57 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_025b98fcff252cba485d+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65982d84aa20c84c91ec97004a8f2b70161dc19442039b7d3b45b734229b981f +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1abfd69d452027c64f1ac9057179efe087107ad7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6b638aefeadca99033ef7f839949202199f19011f1e61018e5bced90f26fab +size 81550 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..db562ef788fdc30915de171c24d0378ec1df4c95 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298d3b35d1f92a681eacddb4af1fdd02e6bdd529a039de76a631acdfbff8d68f +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9cfc1e78ae7ef3a4b24e28b37a51658009ac118d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4769f80ea99193a5d47a246f17dc35f46bd20a97fca988705cc73ac9759eff4 +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd7cab5e446deeea38d51590e68181a708706cca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0677a23025fbd7931d9195daf02d5312e2da1158a7927ddd283ee33bec101024 +size 858046 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6824c454ec2d20f885be236afcf1a454a05320ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_061f22ddc7af0a5d29f9+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22c01e02854f21979862b09571130be0a7968089cd9166a4240ddcb7d25e926 +size 5786624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..39751ecd4e4bd38a301daee7d458bec3012cb695 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adacc7e6f071cf30f81197d157059b22c0963bf27c33f23e9d9610917f32f632 +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..839a53667f3f4f343ea297c1cbe012c4264c7452 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1769023600649219383891c1cf3b3c5eb2086dbe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e28eceb37cad9ca93db5b7d4d33ac2b18bc4a10b72fa6f41354d73a93b5595 +size 1661172 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d816afa2abd2658172be706dd3e8f82fdd35111d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_097b7e476646dbe13102+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf47c986e05a6b4ded732905e78b6b71cfd0a4c0ca2d802a0cb3922ac35f78d +size 3881984 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..40eff9e5e06de68280863f354dc58b1f474ebd91 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48c060bfc566a2808b5ac053f2c6154a586b957f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce55f9f3b779172d357a166157f85e849aef70cc86fc56962d5dd729022e4b4 +size 773433 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..62d24c7aa08c4b60a05048a9020aace3028272f0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f0e297edf120891e834496626c5249d3a4c8b3d00fdb313de6e8c25f5f3422 +size 6237184 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..88c0f9d3936722ee015901655cd1eefffc11dcf0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0aacfff4eaf4af570582+97bb129f/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f130cf2e0d4e49d2a5fd646193917cb290dedd28df33ebc0e15f76afa7ed7a93 +size 6375001 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..704708fedf88dc31e30f66f614720a83b8f7d841 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df80a76638714f7b3ae14090f869998613463e6f5413a1c3706af6f60ad19d62 +size 375531 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e6e4d2c7b03e73224b0bc3065fe7a6e07e22bbc6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c3bbd7fc867b9903f6cb1bb028ef67eaea33732fc7afde7b4124bb04d5a50d +size 1434624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7b1e746af6e6e55067773af976dec10b2a05acd4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5062513634c02e3976177b97dbfe83030caca965f6d94efff0074585baa8c022 +size 1521594 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b3fbe0ee7a74fdb89244c0ba48b1b0fd820d80bd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec162b6f82a677bf5bad8a8984a403624ed7e7f8405ed1fd2b89ffb70ba3af5 +size 46541 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..052a5fe066dbc0db1c032f62caa0c132e6d71ad7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ab9e2f02fa29415c2a584da7d3a0dd489fa46185414b6a6ceda1ff02a0b7e42 +size 154624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..20944d74b5cd685ec7b965885660f201eb827749 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12294311aab65c8b1e1b69aefdf4cc623e27bd53029218381ec6a4cf66f7584c +size 162285 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3b2493c1b26278a4a34ae718e13972384636c4bd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..44df9812265ba3722fbd610f911fe0228e6ca70e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b93fe1412edfe43e4d0b824ef6cc3a483f918e718f8a2140d7e8627e0d8e510 +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ed7d11536c193364516bf27a4f5de2053c5df5d5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f259e869c3d6531c373+c2cadba6/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae0036534d76e1308381c4a5a3a6429b663681816fd0898c056db27711fa981 +size 31171584 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..feb38f9336dd3be69c45d0f5e6cacb6b71096878 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfb1031564220fbc15ea84f84f3e9f18fdf944af7f7d4ec99c1a7a5dc08489 +size 81006 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d82017293d30b3ab28643e0391cf340c913f781 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89157420d03816ac2f9222a89bce907177f1a5ca48f1137c20a533f8fdfb10a +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..66e566163971ea284cc8f027409911616b1e7982 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02bf62809adc55ce64637129b796e84a3032d0036f542bf94e0f21ec5512b0e +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f1dcc172b637a7842a3085071ec1f5c0ede2b2fd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e6fecd547e8919f61a673b54a175c4eee9fa33b8a93f82e2a7bc3ca585e952 +size 874711 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..330d44757f10b4167a12f9077c8dd4a1aa0d3fb3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0faba5d4e9a33c984547+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9c0d90c5c4235c7dc27de50def577fd4fe7b292669b6019f8d21e54f20cd64 +size 31028224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0a45ac96b068b4f734e5b95c5c1a70e2b0421b53 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952dfdff0640134652e8907767e25827418409d6741f69a15c42ced982ac907f +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6d81a5074c35852448186920ece83e204bd78f87 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9fe9205b7b08a6659c20a690e737079ec28924c4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3644d3a934ba05c8e98acdb2da8a63f46c70f18baa46f9904fc3b29a58ef16ce +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..659ca112adf9de579aee583fa64e042cd6ca3726 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1845adad88a4d5ae3381+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd13ab3d6e75b38f4b6611de0bf03e1e699ab03019b554122deab152bc17a6f +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c4dccbe1d2bb154396c4f2e11e90a4ef6f5623b3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5928e1e3d71165915a25d2d9778aedfc58cd57ef9ba8621279558be58e16fb7 +size 136713 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f5ae81f4dd5ca9ae184522d91afbef8d505bcc2f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_184d4ed11977011ce5e7+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8049cc5f3ba1f19852a0d85515d2cf31cd6b4ec3c6781035d679f01bc934104 +size 2315264 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..411594502dd598133d11633e47a660f41b4bc2fa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd240cc4a05841d65b1048379c1685964791ed5c532c39eb202a9d41acc13f4 +size 131996 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5468bf0b8ad489d1215ef2ecc721636ed168cd8d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1bce819dd943e86ebacb+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5877e7d3d6af1d8f7e8e8c85f364b45abe57bc0cd8764fef18529242aceea36 +size 1281024 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a2e980aff2440a892cc8caef0bb1b2f04dc4b43 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90460a3951fb3fb92f159e322d4410d84c975043323d8ddf47fb66e109cc0c52 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9dab9058c3fe48cef0ce354944c3ff889623cbe3 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f8a9f009f623782ff35dabeeaab840ffa02e24fc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332a9f5be929101fd9b4daf5e31dbfbe4f953698ae1a2f981a832e76a33b9622 +size 772484 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..eb9a222efe49b406b91c024bf76bbd727892c8ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1631d9704457551bb3ff42e765aa7514fad478f7eadaa1971aa7b94b7533dbc1 +size 2018304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d567f803aff29f344308794c27aa9f697032b75c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1cb238717180fb6073dd+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71535347737ed3efae9ba23f072f45490b5353400eb86ce76280ce32f5b92bfa +size 2156630 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f612a99c5a5aa7011c67077af4159246a5b62b96 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed7e1763d2fde0d0bfdf8790eecf071cb45a47c0486921354c5beb46403b026 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..011b0d7fda00e58143e76644f75ef7ee615644b2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7620edb3b2c01abe336f904cd409b85732204a2bfa44a10ccba787a4a0b474e7 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0d91665327b337c8d1017ac4178f914b2ff7653f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02be5680d6270885d87aa35ad959e4e5c8554a8c16f2d5c658c46496b154b7a +size 69728 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..68f640bb34660fe224d56b3ad546e51027ef5fc5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d15344e3c6cf89fdff9db9a509d516e5724006ad608211dc7ef73d384471b3e +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4d17f0b0f8967b7746aab548f3eafbabbee37f39 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fecdabb646a7a4e95b4772d0d8e7fb8f0dbe3096483381b353733a751fdc4bb9 +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9e22c8cdad672f2b554b19790a5f92c560ddabc6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6da43545b6d9856455e6319c643a83d46001a0545d18e21faf9fb8834c1ae0c +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c5cbffd36f8a51ba4555e6619d221f4e85c8fd21 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea6ee6758cc98aa0e89+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13fc0a07b3ff0f4bf204a5618cd739509cf5a5faebc9f737ab8f3a8f3ede44aa +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..07ea5de8d4ec025011e713c79a814335038dc333 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb3f3c80a1f760b0f801aa56dd94adcd18f8703faf4fbe1cf4629086b0f3ced2 +size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..742722e53f4fd051a3749048f32e1f71c0a5aafd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcc37564d8330894550bcd1c560c819f27452fc9a2dccfc5012d25347f52f7d +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b09a1b5945c04edd50d854098e0642f2885f6f3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cfa8e742c4893766c3b63b6971e73469c20ed6ed959007a32f73a5d6e66751 +size 81550 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..88fb4cd9488b8ae150c81e1931c97fb910e5c5fe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdcd77cff67340f006b364b59a633120708a4a0875116af0d53cc6f7db617b1 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..542b1212648a82b1725cc31bcd52570d9c591e50 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deff04ad37ed2475c54f4332a554e7753ae59a10d5ba63dc7b244c26755def16 +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48c060bfc566a2808b5ac053f2c6154a586b957f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce55f9f3b779172d357a166157f85e849aef70cc86fc56962d5dd729022e4b4 +size 773433 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e25ff158905791cbdb93cf6224daf81fd439e86 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f94cffdbfea4fc0336ff9ccaf90dc03a7bfd77d3a71be20313da0dc71ef9497 +size 6237184 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..38d09ae4d4dad4c7a3ffca6637aca99a7057fb57 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_225aa072d587f98b83e9+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bbbea7128e540afbbea21b386c191de188036d19746af61dc98d04747f462c +size 6375001 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..152fbaecc7d8e0da810d3f760b0e09953f45fd52 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04b389baff4d431c49333fe1097c9bf015a8d8f0e9ab7b2dac8b6c470c50275 +size 79198 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..46bf13757be27f687533bbe52663054aa1449305 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c09b60673a5f6626e5e43ee91b19cdf385f2dc3113114ba3212f31b086f1fc7 +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..aa33d546563690ed627a67157abce1c79029e277 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6979a724da90b05c60b1f6049e232b513dd03d8d1a531e9c0704643c8ca737ab +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f7ccada5ef9e273d60c3d5fc097d8849b3bab5b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2a64d32b54877e99711d708a1d9c0c4b04b1ecb41005b90452a866373db9a5 +size 69730 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..69001c9a04936cadcedcb3519d3e825865fdca6d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e08f1f01cedf071be921943ec1f121790e4e1b4ff554ac5a157c0750337903e +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e7f20402f8b826a1360b6909b3385620429c9abf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aada4274950d1284626eafcc04cfe8254ea00fabe4dbb0bae9fe7aae1ff3b24d +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..106b41d7b61ce7e9fa292dffbfbc510424535e15 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f1dfbc537c18584ea5369c62ed65228ac13ff53bde9018ec631149558fd6d1 +size 886242 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..eec63ad0b74e4a6b01640915d9520b6ceceaf824 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_251684745b0a47fb333e+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7629a9733c338eb2c3e2b6cdc7eef337bce3ae9fc39ef7498df24502c8ff94c1 +size 27372544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cc99646ebd68dd496f026d8f1acd22e08ad628b2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b48e07355c617bc22621ee00de7b4f93dff6de0c903824675c3140857a0793 +size 773033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3929331e9e493189742684d53a1cc6ad9c0106e0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c7d6a586432b3fff46f9f556c01d44ec0a178ee9fe3076053e86a789f50c31 +size 3113984 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..75902d715e1aeb5b40e85f68ca153a14861c63ad --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_25b514ebfb24f7862617+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66f4d15672a836e4c406438cdb87324bdeab2162f9222a2a67ddcc31b470522 +size 3251801 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..419f81026927d042f12dc056c93cc96be9fba1eb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5674bcd68065f056894bdc9171746e715d51cccf06f6813893350bdf1f4f5db3 +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..05d17b15f3dde62ddbeb6352d704c4fa97d8d9f4 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aaa604e938fd44a4b5268ce4abce8f799574ce04 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4293200d1f2ad90a66c02cc4879fee2b3bfde501b7151fb610370054aa2c3da1 +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..47c53bba9cbbf4c6148338cda2393f7637c835c4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2716a18eea591aaf4f20+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d4c62cc926302eba61b35b1e5cb663382805dcbd2e250be83d3c6a825f05b7 +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0bcc425c828eefe983f82984c9077ccf9602cc5d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e4138bc92e0c05bead88dbaf7ed10863d30ec58495c70ea655152b19e2af92 +size 757178 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d40b537a0bc2d4ec1ce6c02fd72ba8afccb57b80 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27b73ba03dc7e3a65afc+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afee85f5c16df459e022cdcb729c50a3cfed029767ff5daae0be949f54a13ee8 +size 19938304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8246040fc6817bbb107475d6c7d923db02050b8a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b496c63ad93ed914609263ea09a08cabdb784d4f41aa99d31c544d459d09eb +size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6e46d3af4d303f1598ed3df0bb0c8f789ad8d80f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d620a6353912cc334a15251c3771e49f7101ea25fc582e1ba11f5db4f4ada552 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..53e6c1ea9eb6ba3979f5354d81db9ec6306c9754 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bad8cce0aef7eefd85d29624a01be2a07ce8aa67e20dacbd17a14186ea0daef +size 430182 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df700ca3b3956e06e0cb7c5cf2004db51fa1581f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4be9f40c1db625d9c6dfa4d66746efdcb10ec00260f6623a94a751b5a16d3e +size 31120384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..74f4328c100742b54a0da08568c623fdb58bf8d8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291711a5dd69387c68f5d90c715f4279533a4c872e22ca0cf368e4e452231d49 +size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a0f98f0612db6bf34905e5bd353636651630cea8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21068e94ed15da4166d08503c40bbfa65fb0b048bb3ee873fde12b233f4ae681 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5e8d7727b0511a350878469d52667f508aa8d6e5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a19e4faeb0ab97b7be4e7f34fba5b4bf0937fc70ceb6cd406a20798082ec49 +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f9085a5d2e9b32e5ce9d78f4f7ee0851fbf53a40 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2b02b9bd48b487eaff7f+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f2af00b78e63585aa79faf96bc6c252f88ac89ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc29ec5d057780933c49deacb056003faba7a066c72bf7ad4005cf3cfcf5b99 +size 84647 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9f6058e13544c640fd08244de9bfb2553e6f126d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2d129075eddfe8e029d989987096dd7db9021c607475024b045bae3e3c9de5 +size 195584 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a45fcd8894146d3b4967fccbe2fcc0ba48d9131e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2bed80089cc0d5def73a+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338e0e892339fea2aa330bd559c1c5cbf6fd53404317c11e4ab4703896b62c1a +size 203354 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8f7c940b12c00697b4370cb273d06e0d47e1b510 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c760a15fa5b85a7326e0c2ca00c2da04cc5168201b44a9785b02f46bd053b8 +size 84033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4960e4f5d2f280e3c3c96f2c9682ebb832201a4d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324ba0249c4f3c8daa857916263d84a13942a8eb39ba9c55b68c9e19622348e8 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2f64ca16a7c74be176eab8c10fcb1815a72e6ce5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3635339eaf324f1684932551eea4948e0756192a52db41cf7777fbdc3022ac +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..df9c65076c1ca2b5b86c122ebe1edc2e16d5ee56 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205f1c271ab14351f6f4a1e4cc72990f3667414fa57ac67360d3d5cd685f6cb4 +size 81748 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..73dbab2efd6ddeba5786cf860b39477ce5f7da3e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcc0ba857eddb14a136b45f644f4e25d7825f34b94b5918baec5e78e1b46b4e +size 615424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4c959145a2cb21206bb751f65e8f1dad7a5ea519 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0964ce78496680872c8f72132bcc1622808603e54207274325fb5ff399fb7ab2 +size 623263 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3d632eeb2d0079a9127c7bb3bcfe943348eb646e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d93d20fa61a0b1774c81751ae669689205e1ce1d74e195214aa95ae5623ce6c +size 2143984 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..87d025ac7ca3f12c0eaf76b716e1fdcb7f709988 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e79c5faf457fd022d25+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb94912614a59b8bf4dae70448481973fe25894e3b3ea66d75e8caa7366f9d0 +size 3482624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..39fe4ac1b075f968dea881ec4d317033acea029f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2218fdfbf71bf29afa0ed05cbd601bd253eb224b8b68b012acc92cd349a9cfdb +size 42250 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..02623580a92f2986a82d058e771cb3d0a5146d8d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01ec781276063d1550d6620dffe2d414e727480955959ac21331622c17ccf53 +size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c405456691ce1123c5dd9b686c63ac696cd4efbc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1d4d6bdee08e32a94cb51eb0d019d7f562f7dc69546a7cba310828a021e389 +size 172461 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b0df83b6187cf8e1f007970c04e27b6fd1b6f5b3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3dc5884bbad043d149a0439dc8c022afaf39efa8a0d539f1e7c41b77570aa7f +size 613479 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..75df8b144941d0ec6afe12e2fd845e37b34267ea --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06bbe82d5c6809fced9f7fe407a02f66441742c9e1786733e559a37761da4f0 +size 1086464 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d45c10ea5211593d51b14d0b31372f54af1bd13a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_31652417a84067caf6b0+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b4cb268346a663fa458b53b541c5ae6912cb442015a53c8accae57a113a1f9 +size 1231490 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c95e41c90feb941c61b17a5e9214db5132e2bc9a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93332a3023b3043f3c7d3f986b201671027d584c5c981dbd3a81f9b1c75b8c47 +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1454977989c2fa71c93b44467908fbb896400e21 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..97c8e29d3bf5e3fd6600e140c11a716b0a047e9c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4023d2c4fcfe210f7e7bf12f13b81ecc071eebfc958003de7f2019f4a46569e2 +size 1095125 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d4f08e9d59d9a8eadf6e24d5bdd976059974dc92 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035590926b05a7c9b247a73a2840fa69821d269f3c615e3bd9e7e28ecca500f2 +size 4885504 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d06bb55a2f479f7e48f162d13e0e72639fe4fc21 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32d7c444ecc189aa17a8+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2b4b2ef02c3b256a2946166cc7c412d628696938d557a9350c64de13ac644e +size 5058549 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fc29a02567413824ef764722147eab2ec927a1dc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7fc55dce818e0018a135c932b7585ba00223394472dad7d9aee08b6abadd281 +size 84033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dc6f531f44ee9cf8c367a6c042991b069a2c43b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46868f9c178581ab44357e7b137684dd98ff2c1aa3e587a9163a59b45283eefd +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..11fcc93f070c69ff1bc807b59a4cb90ca848e067 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d52a08fea26e2939142da8d2cea2717e3f93f3b4d37637df3e97fcdf260744 +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f5c6841df512c82920e2bd4bb66add9e81430433 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5d4146faa890b92be21e8d89202498233a162ed015a12e7b14862f458be4f9 +size 694657 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..73639e4d4c899bc446f9c311deedb8d76b90879c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db38c3dbacf8dffddd1a131f519bdc432f2789f24be07d612ec84ba1ad86e7e +size 3533824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0bcc69c52ea9550a11cdbf8de1b63f6d741470cb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203853af4a81bc46f26c852058a69008bf1d1640987f5c88a0b498e3a13ac7b6 +size 3663806 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ff00987ee182c554d9ff86d8fc2bae220524ca62 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270799a68428bbba6689e3ec0f5bc39ba3102e97812e7e7f240050b4597f4944 +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..575e981f7f60c14b7512f0b304b87f4aec13f1da Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_367840a31061aeda6f75+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7a7ad5a4922a63d419ab6bc0bd85c96579379f60 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bc2e687172ce773bb1571f90434e334ab879bed5c8f42c7f7dd386e4fe2157 +size 132618 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..487f9c6c13377c9f835648803d0de79be198e703 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3816aa1fdb03c5072bf0+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1f3ae64caf770faa653d491add8a446a414444b80bad1aa578b8e1674f64e9 +size 492544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..357a09cc68ca787b762d016946e1b412289ddb34 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785ffb37d0114be58bbff93596d1905917de36982edf639ad3f6b98cd5e43415 +size 82573 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..36c8e8e483c611c945a8f4104c982de48893bf5a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2aafae91ecad0ad9b888bcb669b64acb2929ce33065e9452bddf2d2d8ee4a14 +size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3a937948727ebd33b6e71c467d98be772f9f4205 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004a842a6a8f26ded0c2a3c6975d382b36cecd0007fc63d53f39e61f0285c1e8 +size 1037449 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..975ce27d16f059714def1027cd9e0bda00ae20f6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_38a491bb249cb0a65a66+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2c3f962dd9545304d485267b9dec3f68a33752177089d19035c550496e9d99 +size 6626304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c93e099f8fb82b7e7846132de8c40ee41cd860f6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa45fabb946616a68886fe9aeb9bb07e2c6e43248917cebd742fcc759bc6ca82 +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..168e202205361dde465a8b78023a14daa268811b Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0eafa468db2c25854d95e3c965dac916b1fb832c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd3e2b465da216e06812d8519c549d2f4d85e75c2444788e739b16dd9ff7476 +size 902833 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f98cc588d1960293ffb4a69cf0a265ae49f461da --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d49387eb62a527167633c8b7eef0a84409dc680134517c0659cd5e5922ff2c +size 7506944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6b8c34f11e2a01e50ac09f6f9a2dff92c85dabc4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdefbeeb26efdd55127bbd068f19544140195de0aad339283a664ccf0935c5f9 +size 92682 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dea732bec7cd2b71fc2602354a3f22a5d21cfce2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ae44108fc0ad72d2ae5+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2864a6d5d73efc2263a744688341d5cf462c3e5d2a117422c8a3c1527297b6a +size 213668864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a385f51ec93783ebfccc02bc4ef8865b40ef8be5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1c18742fbb646d4a81924eef4eece4618c7ad8f1338a434846434eb796d5c5 +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..17ece38a6ab9f02c130b160ea4d913640f8d90e8 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3ed160209074742a9f74+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8dd4666666bb38ca96f9f028a3d44dfd55b6ef7e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6467c23f65b4e1cf85e7d8d42844debee91b8214cf4662ed17d093581c5cc12 +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b58bc15d39dd97d877eaff16dad024c563a71805 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3fcde42e05c364259ae4+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c564da4ed513820fea7e8a765005c4a821894e8798cbce881638c90592aeb3 +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7787c6da17981973a7adde99e32aa60596dd893e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4785fcc6b48ba2c44706eb573703abfc4a7eafb3b15d451691d7a85fc85fdf +size 7092 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2ffad384663ce2da0b032949452d86872fafabd3 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dfc58cbb09f7504b3f06e77395a7f879c43fed31 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a07b079173e59dab3646d1db7df971e18692f3f815f155e0dc1e4d6006dec2d +size 89438 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..56f76c1cf02d0176f59f115ddd70efe67bf76a37 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbfcc60f177d83d8e82818d25fc28525c2b150c2097dc27263b0a23ea2979c6 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ef11ed528c2d21cff44f113477b3b58aab8a0dd9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba64bfd493b560ca1a13cfcd0d97c4df4b18f10af4c0aa316e29d0f914a5d5e +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4e87dbccd446f95a6290b493e397c985ab5d8263 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8145fd956affb7211805cb337a58ab53054ac6095986abe305e7007d28d295 +size 89438 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0cf18b1fe16beeb4d53f82ce44cdf5050a1d983d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874d8e09c6f6e3973eea15d6c7e1c51b909c71c4f9702a000aac510b4ae92e43 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5eb0e13d8bae553d3128e3058a58eeb4661a2acd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb6bfb6ee9cd91cac6f75c99fce2ae366a2b4c9f5b5037396ded429429426c9 +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..03548b82c0ab2db3fff16a81b87d2a6f6cb46a1d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce900c5b6f2ef81f75f395da87b22ea27b955c2ffcc9979035b2e6953b66f0c +size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cd5560759282c09b9f23d6a7d638e25798106d07 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca474ead7f7b0bc1b92cb0186f196f4b08d13965d75b129492a50925f1f2d3a3 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..619394612635f8be14b36ee82d229dc5bff4337f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccbb8991ce4c08190c00f2f5df8080b34521b6b52fc50a720b11ab9f0d4965e4 +size 69044 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..692bc10dec58b206ccaa112ae651dcbb650b3cd6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b6371144cf9c14b0241c348d02996e5997df9694353a59d7657009aa4a0626 +size 1168384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..526d8cd4ad5647654b30199c725dd1ade08cb25d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23873515e9b3ac41346ff4633bbb3792ee6d0b87624a52ef58e92011057e3277 +size 172535 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..eaadd8bd4c17fbf2ed7857acacf5472af865c2e7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46df7985de24ff1ac32d+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349c08e43fa0c734591ca5c58cdb9a3faea7b212ba55185db156ead52dbaf1a4 +size 2274304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47fc059ae1997876c549a6eb37b1b0ec42b1ffdf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16531d760e00ccb36e70a9a77d23a377a0deec739a0cb0616c3f449d7352a90f +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e3ac30bc70d3ca6ad1db6662aeed09be8a34858 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ae7d9f63f0213e12f8df57c87b1421810bb9b46e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232c21d6d4408ad2807ab3e07a582a93c1ebfadb83d5899bd26c46730680523e +size 701615 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55636d3a2bca0f79c3668e22651fa7a3f0f48ada --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4aad761989e914a680ea+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1227e5c31fd7b4bce1b4074442bcd4b2b2e810132005cdc344ec27c60e48f120 +size 19631104 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2cb9abfb8e1ee1c3a50d91035b5819017ac4f072 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cce13c2c8d6e621050c4f6d2a392fb09e41dd7942671696a8fe6a6738dfe181 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..95dc9d108b7a7133bb92bd1cdbbd17fb92ff31db Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..d0de290d4994cbbffbdb4df818224f3488d981f5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ee5302006f5261c8a5364810b502e977177edc46 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e09d3057909f88c501b6ace030dc0d43bc4438e83932d587b19098ea653e9d +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..07b0b9bba7b31b6503b216a4ccedcda45b3875ce --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4cc296fe1b7abcee7c5b+8afcc287/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d53f1696e8ef5162c366e0fcfbbaf608ae7bed8dfff739649d482fea118be1c +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a9edf7c07eee7492f09299b1504b8a8e8057215c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9892ab17c6774324486a078fb89da8c211495929fd88b6c08aac476252ec7aca +size 773033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..baa5bb8cffb53b11be20a272c0305f515431c3fa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2205e1fb7956b6c78549ca304ab2e432a4223d7cdf4ef3445b579f18991224ed +size 2499584 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d2217f7a418fdcba02761194443c865ade8282c5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5011cce3a1b686f14b46+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d748e5bab7eb9bbfc7970c4d11ee7b29d507fdba2f7593cb5e6169ef10c4f1d2 +size 2637401 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f4fd75a2a4a87c7f710f974f74f2dbedd511afc7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7c9b1670c3836875f4cc38c16e9fc16d27002a4f792d30a31cc1494274c3bc +size 690270 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..acb3c198a477b12cd675d865bb92ad6a5dd85727 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5625dfa5e600d8aef4ed293645867163112521fe828fc0e5856335ec28d4a4d +size 8827904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..de540af2871da302b9f59ee3ca8a3057a26f294d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5062c09b51ff9154f184+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129017e8e9887bc15ef819527db3044b0bac79a328316a8764f69925a2ed1a46 +size 8965270 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2125dd117f8003a3eb43d47d4ebaf3b89e2a2059 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dc89c6b2f228783a4b7a847c419d01d23623bb1c36c7346580d9b8f877269f +size 456914 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fd3f30a45f7c18cf8857511196d8e984c32d92c4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6440704e13e17efd6a9115b3ee8306b3906f06fc8106d08f762dedfc26408e +size 31376384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8adf7031949e81ac990ad3aac9dbd4802bf3bff4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89337aed35960e0398ba1681cb4f79681185f5ed665e309d466fb739258e854a +size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4d8f3479ba16eb0d556db22ea513cce3c9f12d45 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add447718a0e91bebe6c9fe36b99ad94d58fc390fd60081b5084acf0ebfa6f3c +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..25bf0ffdc848f50be1bd167e231c8b4a4cba283d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba61c6d291ec0b9899feaaf7fd7f0af72ca6ad6e816b7bcde96849f93307a29 +size 843436 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bfb3ed8cd577524763afc274665ccd228539c9fb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_57e3cfa23bd65e42d62f+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba7378f7fee82244d0057a8d4f97c6bb2f886fafd3fa380709a9c9dd8587016 +size 35533824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0411052cdfa95b344818a8811a935c496ce9e694 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e922a688c4f6359c90d7f7c743bf6bd312ba9ad617231becf02cec490eb8326d +size 51946 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bd52c653d8f5762e01ade9ed2f069497869146b8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39311f8dea15b407c7820c48887e5274479782b917cc9281bbd0f759f206ba83 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d6a9f07914f6426dd66dd4a1b5c8d4772d0bb0d4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd188af2314d5a7eff13ea15abc949171cd513fc3e3d699549f36bf39dd1fa32 +size 195507 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3fd0c8714c069297049c2f1265558ceac75586a3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d5e644c7fc5faeb4dd6e08572e6b953ffe9aaf266e02f6ca1ad01483807ef7 +size 82166 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c1f2661d413e923cdd1d906f5b269eb5312fe0c8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b55df3ee9866c55ea947a4b661cad05496df3242285ac3c32209ab3f4573eab +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7f879deab8d4006b68d0a91bf5c8cee56e266d16 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a53296578f317d37283+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77171d923c95f81ecd155d404b4f07d35855bc8fb83e575a3b8883081299319a +size 254559 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2305e1517eaf0151e327b8c6f47ee70c7b60a635 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c899b63fffb03604bf98a0ee48ed739b16fd104e5173b07f23baa74d4eadc3c1 +size 843800 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b4bae936b6a6d244631b5475f4104d0fd14478e2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6cd98680cb381159107aa734da58cc5398f26bf6192e134ec7af2a15c270f3 +size 27536384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..351cd71e8997957e0ede64a72807c5fa845feed8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2711d1a721a01baf204ea9e97eb708195a15f240d8bd65b796009607fe80f099 +size 1565304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..65012ac67c2e57d90c3d7a44676e69763f87b9a1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5fefca4728e29af5f535+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b627b538c817e80aaddca5082477ebe73c18498b028bd8aaa50f9acb99785b +size 2591744 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..75bfe16768859f114df351149ff0b3187ab925d2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497c866136fb799f26f306ec90faeeda1b3e41c8e46e710d1086e9d3d44f18a9 +size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..557d99fde60df5faf6eb1ae88412bc557f0fb26e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bd119ee9a0e036a1c56386b59a484c66903d54564c8741482cca0a94f97542 +size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3aa2c6d2460378fdc36300bb97f79cc5a352cf62 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555ed7df9d1c4c5f365542c32a00dc280894a42667f29162c9476643ee32aa05 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..83be213ca4ce16984764d91dc322fcedf2c429c2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3dfba26397142aef809f8b4c04dfead2ac8316b713ac204995fced22707d97c +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9e5a427f26bf5ee5894efd6a27ab24b6982bf386 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfceaa4c3d4cd40b71d3e19d1a5214c3763ccd682e664ab43269d5ea18bbd8a +size 379979 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..aef624e96780b8128a84328a86e64754bdf2ecff --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ee99ed969f1b132ca9cc586347645f2327b3c508bc60094ebbb5ecb4a229e9 +size 1434624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d319aa149fafad6edb33d2db73c3ecbdbcf4b797 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6642d35addb60ec085b1+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539ad2a559b69dc9d11d0151d61aec1e60be16b36761018c710b2d6ac0eb002c +size 1521594 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7941df158a29ae97ca371c2f91f26160a2a6a7f4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce77cf1b3c5ea413fb633521a095badfa4843b1c0154ea2a41c0f3a335caa205 +size 81006 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0fe22e64e38d1b291a4c4719e59494e661f54328 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc6d1bcffc98a707063849584bd777524ab16d99a9b36f43a0c97a8b85341cb +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..91def0f685533e6ba7591af6311eedf398f790eb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dee33a8f0104c3005b67b596d1d3ef787e7cd23850f1ffac3bde7c6b31e3c85 +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e04c4d1590cbab0f681e2026f4f0d82cef535697 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334ed4956be2b358f129ee3db200a4bf138f5001f29d06574c83c07ca8aed4f9 +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1468c55d94b245d3df14a6a2b9744696b6af1e24 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67660d190a903f2f351f+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0c0f835a9225f92e6adff858bdde2e2dc5ec4b4775b9ddb26c9949c7ce61b1 +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6018009af437dee58def76e11803ee14b43862eb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8595de39b60526028c04b4c6d00125d4521ba64bce786cf02368b76977ffdad0 +size 50076 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a989d8e45cdf8d4232e0c3fd3460bf86d69be29a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ff807748f08a32821febafa966cdfe8ba5def5c664d1c6d02826fd2ee94358 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8508b0621281903c9e232c5a5e5db55139cf2c83 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f79e1d9744e31374274c65877eb1317f14db8f679e3c660305986a7cf9f00b +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10326d1598e755b9c444fc7e200e301fa0dbcdb3 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c3996d6ba369f652f0f05d1f183ca3c9e9f32acf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48c060bfc566a2808b5ac053f2c6154a586b957f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce55f9f3b779172d357a166157f85e849aef70cc86fc56962d5dd729022e4b4 +size 773433 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..caab05a40844a1c2036faa8d3a2775abf3f25152 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327275d915349b86fa5f5466da49d9bb1753645c98344b17f688cef2a78df53b +size 6237184 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..48e6c1378f6f3d730c02115fecb60ec36f0c54ce --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e4efecaeb594ce776fc+651dae50/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053b08cf17a262168a05ea5c80012a256d92d76bcc7f95fb55ba7bcd3b248f6b +size 6375001 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8bffe6187691159db2605f30cafdcfcdcf53a100 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc07323d8dbde3248d4aadf4a9df1d0970b39abe7d1123e0ffebab560f9c193 +size 643836 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a146599bba83a46134c7b71185ca33d6d65f95b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc0b3513bc9d5aac316a65397b2ca7cf9324435e864fc965bd48d5b8659044f +size 8725504 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3ef8df0021469c03c13a0cb7c87b682e2e8cb368 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ec54d1cb60ff01fc2a1+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97b0bb5c0170043e3f760308c54d4c96cff4c66b0fdc52d19d064e8bbd6ba438 +size 8862755 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..72151e6c720e2b3e99604524a20905c9a077fdde --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7dce04cf5169e7d7109611eebcc65efdf248fcbd2877b68f27e8f5211549484 +size 1072456 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8f86a635d0094443c0dc6c42dc1f92fa063dbde0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6eee1d2655983d3e332f+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab674f3130a691cd1e9ac273cc21f5c8cdeed34d59d5ca471aad26ace63bbc32 +size 6605824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4d2d357385d47d99dd2df7bdfd21846358549b21 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735a1d142eb6478b7e6eca0f0c9d720ad522d6740d93da86eea2e6e911054205 +size 620714 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df0d3f3ec4d69a25383544c62567db5a6b451dcf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d07069f443efb9399619a4d7a4efb126355d738f4e058fd6c19bc2ddb128c7 +size 1485824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0e8072b6b92c7aa82b4fee1274e7fff169f776a0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_735269a5fa23fa6ad110+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b34e4df1b180c148f703a35761e0ec3f8f81049bf96e822e21347a370af9352e +size 1630850 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..052975b660072477eb170d23ebb856fb58700421 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51af21491caf08ac635a76a5019451599de63757b45aa41bfa9d12e59df183a8 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4be7d899b1d8d8173a19830596be20bc1cec21b7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1842777d30408e20f37794927d5f65c1763e9e05ae32bc2cf68c0dadd27993e +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2b9f372659ef1a96c4404f7e7e73242988f391b0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2a710f566a2d1f59f90dba87a5350c8ee8e8d21aba309ce32afcf049aa0eb5 +size 745782 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2f29f69c7ae427c2ea4d6de6486d97bdb2f7f806 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfefac025bf42101ca37f7d1740c85a4e7654c060aa481339a530960b7e96fac +size 4998144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ad0aa028c21e09c7baee63eebcc55fc6bdcb1a1f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_73ec31085ec199e0bf87+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c85276620308cf543f4c870d3661766b5b6b4fdd85dc8c562a0500034f9b1b +size 5169870 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f6f45609d733e98fa628e247cbf4f4c64040b3ec --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3911b9e19624e2d62f7d180667f966981db8d75fba37e5f97e83efb5bfe119da +size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55268d0057a121cd68028b5e0ae16ca474cd9c64 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1d3978e4569f994a020271ae0831bc5643a917923e45b4c3348aed583775f4 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e72d35fc4e69a33e8c6414b3432905cbc5d45e7e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee3109f1fbfdd51cbb1fdaeab195b1445646dceb88be54a041f6a9f9f96ff25 +size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0aa0d1dc10c1928728e9b014af4bde91b084dbd8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57dcd90cef63c61e270f0399be4d9ec4e48b86e924fb220247452e416e836ac +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3fd1239d4a7e5bac5779b18d56f5cdc43984799d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153c4c8e3aeb51a8152f2031e8b400b02c3f08e93552c13a796d877d91bc7349 +size 69051 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..90da8440fcae3bd8eb664ffd2b5fc808ea832618 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_781e8d2ba7d7773d4447+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b5940b1641b8104318b96a9d9d47dca9daa85530a978c4d57254aeb68c812e +size 1168384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1627088221d0fa812c4a968a72bc1273c515f7fb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b142d87d876dee57b5b66d54c21bf5a9bc73b3d63a32d4ffd01c46fe2c82e2 +size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..721c228ab64a1572b175cb9581b751dad03b08f3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5cb8e6b7db67bf40c1e0170697533b941b247d1324c5fc287abf11640081c4 +size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d74728c270ef30119d766669f27d5568f7d37d40 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4e4745bdc2b2f666f9a371aa650307ad85e38548b8b082c3ee7cf04e28c573 +size 83489 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..72ee4ab9b23d858eacb53ec76014f8351f2bb05b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0224d883f8020fbb8be6d472705c13d81bf4f3f1a27ad3bda24aa3146372572 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ab3fffdfed99a4ac8d5d16069e703fa9e8f45088 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf33660ad2b95a5db5021c668111bd025d45020cf0a23ccf8fc049154b661ea +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9d315b00a2533426122184731c16d10c7c3aae75 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd447798999fbb97fff82cb7a5bd0cc8bf0dc8040472a26ff75021bea7ece392 +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..90d99f6315288179985fc3530042d3f4e443476f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_796c64ab3e80099de463+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:defd23921a1ed328d7549614718da2702e6d68886399d0f6baa4569889c336fa +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca5705803442dbf0b0d583023cfb81ce7ea68eef --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16d58c7f3463cf55f0d165bcf887a956b39d66b631c999c6f3aec58516b6af2 +size 694657 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a1dbad54fa70225b3a6f0aa8fd3139a9913fe586 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1227fba29dd0bed7cf3480d83c198da36f370ba23153cbdcef6b1bf4e3872c17 +size 2591744 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3541318cb3ea1880e3607129d97b23272a2119d3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688c25287376da2c44e1e12a018d5b7ffb0936a20be05b22f47fa25cc3883ff2 +size 2722174 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2149c8b65934ee41538f0ff8bb1de51761e3f668 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9dcc2d291a29395a7d3b0ecd3c329ac16dec5a55d463e1547fdacbbde664e4 +size 10010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1610224b254f298cf5f0e598b58480b909b2701e Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6d65eaf41e0d913ac1ed0ab5b10ef1ebf2c03c39 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ad0025306f4a788a5544f116be695c8058e05259f57ae3fbfbc8978955ace9 +size 1888271 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7d2683361698b14926ea4082ddf87ac99612485 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9122130ad37e5e9b751c6d09dc45e7d9cf9e45740c95fcadf87448b2756ecf4 +size 6534144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..769fe00d2884897c18d5d54e758b2b8481ed2702 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c80fa99c1314097c5ca+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74623aee5b9cbb27a4b291bdc59320b756618e07f60dcb01433400d1985acf8f +size 6965264 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d16df4d61f7ec5889998b2629acc4d936367f1e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61eab86b4c8d3ff91c00c1739d222c4ed2b688e4625c4bd8cda0e80dd81d38b +size 83368 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f84dbe31ca5f0e7ee9964afc1d5c138ed65435d0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a833e92f3439f4b0359cb62519c02c51dda934079f1cf31e8ec2b8fb2f091c51 +size 420864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b3e09794147aa46cb3586f8df0df755a69e7d0b8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c3291c3028b7cc44e790e359a20c4a356dc8317135a8920091635dc195987e +size 53803 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c9f55811dc28e3c37363b9de0fa5c277e5e69327 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04718f2195a2c1b43c763d1c97db3bdca3078632c6d0f8a05ee89c442b6f708 +size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7a9dc8a692981ef647e93801011c423456be01d9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3062bfcb48a2737a12b3cdd6358e20770e22a8ba61c0f4b7dae41fb1f49f126 +size 885897 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..388db3657706d0aea3953708a7e8539eae600841 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_835052e8e110b842f692+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eeafe095804e1ce7602779ed9ca9136b6aac9d65bfd3c25f5430fe0463e964d +size 29891584 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7891f4c9a2c75d1b782d9143d6b23b30bbec9dcc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffeb8e9ece16ac41c4cf88706d49bf0b121145138f40c6107f5f96f3cb6a275 +size 847776 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21921bff2561bdb6bbf49a3af3b97b0e63dbeac1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_85a3b00cb47dd0b8aebf+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134d14dba6aae5338b4dbbc3b448710798a58d8b15010a09d424dfe2f7a911b5 +size 27546624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7a14fa9b04c0671ef37eafe614ec6a7c25b5c5c2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ee9aea0fe9a0404969d1d2793d43b4fdaf9f7455eae8e8d26f597ca0587e04 +size 83489 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dc0ab807fa4ed801936b627edbda12c79d239e49 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4041dffc23fbfabef08cc959c1cd21aed5b8ad5b9ac0dad1a8a4cb6faba17fe9 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8a814d634dfa89551774d83bcfc3c116ebeb0a85 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7962dec34318c62eafebbb03c003a1515a174f5348826c9b222ff2d8e3947dc +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..daf4e87efd4469b715a047e02f75c698c97a002b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0459c9242d2a6cff842c70cb6e847a47bb7524117150a0b4eaacae2e7f46732f +size 613479 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d17e43107472e39b96a5cc760ee39209bc751c8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7004c2f4964ade6d5fd9a8037d6415777f8b39f89e69293fb7bf4307ef9c7d75 +size 1168384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0cbdffe8df12a775da7fe869760bdf3dc02ca255 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8c3869a20faa15ac2c30+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3943566763583664f26b8032b5fa5a1daba09e84e5653e0936ae1b281a2a5a4f +size 1313410 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6573915a9b30dbcf5db8a90a6e330e5d5f874bdb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd24835460a8baf0615fc19e874feacc4edd4ec98afd0a96455d302e91a1114 +size 201977 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ac49c21d72909fa621c00ecd037149c29a4ff1b1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f30eb6ecd87f773c43984c0a179f282de629ded8c4009b3ffad9b070420be01 +size 6554624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..82b489c32873f00d0efff328b76997ed53d6eb93 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61295592ae28d8117bd19aa4bc70a5fc79b80a6734a196ac9415d96715b5dab8 +size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..17abcbee84ddb6d9fad18323bbf91396257925f4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c0e8f392a7ebbcc68ee704af3782378f1111aa933c8f7621bb685847c4112c +size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec9c46cd37bde5f1ebe23790abaa9ed87e6dec0e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bafeb89e81ae1e0d3ef3fb68305f8d7e8397f7dedc90bb46a6095d8e2b3957 +size 740826 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1ea33ecf65783b9190a7c489f2bc3a4a5d867db4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ba3c41a7543b05d3f79c6b574181ecf11ea10519073446ca002faf008125fd +size 7384064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6ce4214fc2f2e5656b37df3a76fb41eef5288bee --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337d1be5930633bf22e1826ed29d5ecba2142850ac40f4663625c98a1aef4cf6 +size 7578631 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b46a0202f2245ea5d0eb7edf578867ffc2dfc5dd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c454b59206e26963451e0e80eca796c697e09f26206f2b7e9bec24b30d02beb1 +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..508420a5a09ba5c71d5dafe7b00918fb92fb553f Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3bd8cb730e0e09d9a4d4fb6babc098cbe8023263 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457dbd6282732a78ea32ae3f1dd8750fc9a3f1d373b4cf9b6dadd6a344e5cb89 +size 88270 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..86ed332082101652ce59c2a200ecb8fb4814501f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8ef8846d75fa5761c030+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4624cda2e2783d6971cb4beae805e21e5ebb2a9bdbf2be6f4186cb108328f532 +size 277504 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..28e9b745179463bdf969f78e1d529f15653868b1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..89b381e0104a24c63ad19905c4986891a0bb09bb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7e167aa7ccd034fc9c89f5ad9e1b7c70c446c20ff2575df0e2211d8eb5426e +size 410718 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..44930b780879e9685f9edbc28768de7dddecf942 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e63314ff7255f981bbd68fc19cedbbbd15afdc387680049b8d97f3c03edd4bcd +size 2683904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c1acc63ab405adb5bf1f182b4caccd56f915cb05 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7fa4aadb40a8e73e399a7a32ec42f6c1864223e526e8d67a3acde8dbd216e73 +size 715372 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..877fb4ee62bdbe6aa94f62a9749e212a959620cf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb80ba5396ef0e2e659+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4773c29fde2ca590ab193da1888fcf6e32b444a62c5f816f7ca01ff4722f2852 +size 19835904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0063d1e7b40e03b200d3525f37f835d0cef47a44 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc46c05376f00dcddb7d727fd8f617bc1aec6d53cf8fc1b8743c6e312169ee0 +size 582901 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2940b2b4eb4f18996c5bca94ce0c808f948acd7c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e653d8dcdcbc6acea1404250651d367be3c077231d23fc5ed2255ed127c1c3 +size 1444864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f60086eee0a9f07dd80e2a1d3600b9c79a571515 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_915f412a8437431eb2b2+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fcb0c8a16816d04018b225734cdaa4924d56f141cff49b86c6d83d9c278d36f +size 1589775 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4e40528b2c1be3a27a14449d0ba0f52562443620 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c0c1dc5cb13b2021125ba93d8b556d84bf6c87a60e4f795c4291c81fe88f5a +size 745398 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7cdf73e4e939615292b01e39d20b03603aeb1221 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c5c1d5d0b195b6bfd1cc96f77e336a7dc7c21e2eed0fde6e08f1c9c05b55d1 +size 3820544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ce003f78a177a5e3c03edd5002221145adafab6a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_92cdc4fd3b2c266a1f01+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb18671f4a5a4444ad1077fe5df0c4c2780f1297bc01724d237ea14749be0a5 +size 3992270 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8995a1e1177bcf1ad4a31efa6ae0f32874fef736 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdf4d53539b2ab9ae9b1290c72f0bfa819e9b3d8eeefb52a0037f443f5bb474 +size 132615 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0ee287082118c68b5427558c6fb31f50f3f5927f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9430ff6a35fc239154d1+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85374d486908f16bb109c5d132c72b094c8eac4bec64d99c92b6f9f2aebaff89 +size 492544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..31998095ef5da96d478d824cc63f0f03d7474ac1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287ddb67e3d9191bf1a53454e958ae2301a287dc4b2b02047b1637341772e767 +size 745782 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8b68c1cee78c5a5bc41b7d59ef606a43199cde35 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b27c9c07e348b863966047feef36dd6726f08397a79367c8ebdca107df5342c +size 6339584 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0f4e2bcac16e9491fd498d8cb0ef92235d758f43 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9461a71f0b134dc8d40a+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251cde90cc98ce530bbacfac62e4d22c0447107450128460a03fbb5aed1eef70 +size 6511310 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..21ec3dd36acf696ce490381ddbf4b3bc612add5c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ff68867c5bbfe5baeb0ae1da8e8c750ebf33f6b0a7eeb15b3e321e3341c207 +size 1910639 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8a0365632e966c04402e874fd4dfd92ad1d63c39 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d28013bd783aed785e0a65415bd3e6a302b9e71e725e981673f9578b547c82 +size 6738944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..db90daaef2c33ea0f56fada7c120ea9eca0eea7d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_94e031bc9e9d532910fa+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e701f41a85478a6bf91c13c18d8210ef864faf4379a5d45f67b84374f68df9 +size 7082519 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8bffe6187691159db2605f30cafdcfcdcf53a100 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc07323d8dbde3248d4aadf4a9df1d0970b39abe7d1123e0ffebab560f9c193 +size 643836 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..19f14bc663f04a5f5af353b7304062f3fd97fe79 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0608993395a01bc5bad1706fc6360f1eec0a791b250e6c6aa9d5bad4dfca8a01 +size 8725504 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..799db8bc3031b12473dc63aff2f544b108c38b1e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_951c8a5cf15504464697+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997a46f7771c6ebbb8c2e04128eccb78adc3b01a8b9fbe7ec1621604a482a110 +size 8862755 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47c37ed63a214364892fe16dbb18a26acb5c9542 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bd2354b87e72d380a363cd1cfc99ba880da6cb454791b59fd1278345941946 +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bf4c14732768a50c46be5b0cf9124efe046b04e1 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..465a5c9f13c760886fc4a7728a5aaf3b20d23801 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1d004a3cc933a8e48554473fa7c83168bdcfe66f5286ebeea67f8db25e30ae +size 2327880 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92ba90fa6fd2f4d64c5d8e90323a292c82657e65 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba292be7e7e441b703f+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0e2b1e464816f528cd197528a0c07a22ab283512fd6ed5f87b99c561f8073c +size 3390464 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4f48d0e4c0a3638f20c3abec48dc38cae565da85 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4350dbb3041c33ed2ed3737574b565db7f7520f6fb9e34ae56e777eb6b606e +size 132612 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..94e66284b0c110a31fb9a5b5f09b72987df64a2e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bce7228204bd2d4577b+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5eae152203c896ae09a37b003b33abe4866d0bbb60f43e383831921e735a00 +size 492544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ac1c1cbdeb45a22e8c938abfda2a718eb2f8ca82 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba6755f76044cc182adbd3f58b2f88e3647ebe64d521e294bee38f33cd7d099 +size 82571 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a7036c035482c95fe179591398f40ab70c3844a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ed7c62c7882a05f20a82c1070ccebd3b96ebccab601e9985d0d9d470ae03a2 +size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1654cfc00a632ac0cb2fcf75f4d89dd2d5d75c8a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a1f8e05a86a5c8f515e1c034a06442d19fdc3f1674c0fbf0e3499011b528c3 +size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21da0c1439b8cfc9b6a7039588fbd4d8c7a400b9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d25a3804d66b7ff656ecf5199d0baded3622f17e660ef4f4736e8734c1b0938 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eeda5a2da7396c5e19acc89c719ce651f7aa08e9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078b037ab70c04069fa78a3ad21ecb6ea967038e30333d61e6905f52ed3b8ac2 +size 80327 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fa00256331c0cabf14d56a463c8d19d3b5f962d5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf462cdeb496241af30d672b2e4f91b7541fd490d67691bee195c614e1fcf79 +size 308224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f767a06770c98dc1cce417af3b62edc988cb0a19 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4b338c58fc56e5397fbe8016b2b3780f5a925cafeeb733a1e0554aae0c5e48 +size 319522 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d42d73f3806dcb7a42baedf258b1a80f75180d4d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629fec42e604b41c6affc929b90f7adbce8aea2a807e926047eee9380557a3ec +size 417088 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5629b4356295d92253421403b140dc57b4e15466 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad71d8b6338ff2c14e47e9b22d8cfb8d91979355c7cf8427e6452fd95f370a2 +size 2233344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2559fe3b1db79fb84eae71fd231ba345d2f05441 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a063942b4ff1b0d8f4dc+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef2a9d2c8684d1a2494eaf6e20339f67a87ce9717662b111f9434525ad99ef4 +size 2303088 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0b18d388fef41446b30f69fc7c77acda68fc6d49 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f889f3afe3e6cd45a6bd17e3ef73dc208c21708fc1dd1ad3a5a3c80d5a1b8f18 +size 201977 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4284cda963ee41004aa2ad95edf9d5e5c863f3d1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d13aa2dcb5a47e0636e1b771c0bed7e5393d79b1c3adee5f4e96570e43be2e7 +size 6554624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bae7532e62f87dd96aeaa2c2011979cf73338534 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b160039d090f8d029b08fb98b9ef3a9477eb4389b4b08b4410dd67a09e9af6 +size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a1a861c4ace0aafa314e00c9e59e651a373e19b5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4972af6f4c52b9f9229ad3866e5d54a272391a1839aafc8054159655bcad7619 +size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..20009efb2e8508fbeb58fa71bb0e83bcc2161b97 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e251415128048f19616fce8b11a16250dd5b8bbcef958304e73dd3e06731decd +size 88894 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c15965095c8cba5111015087b355d4641c3a756c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1f5e0c4b538ef4d33b7c9c03dd4d8c636770d739a6395af324e36dc2a9fedb +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..99896f8625b657e4bed8991e55de90449186f481 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e47c8d6011c2921e8cb2c32b61ce263b5c06e42a22d81ade3f0e63d0c49776 +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1f84c3b89b02315c1d279608f358dda5906af751 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef71906b1d021844eea2415d9928668b43bf018232964fd9029a064bb9b0ccd7 +size 136009 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7892eb8da2a6155eb3dda6acc33924c84dc59f36 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a3410e1989f6ba8dd0bb+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9175f5fa3964832e96703af015bdef337ac74d03a8d50b3fa6f9850f4b6f8c5 +size 2192384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4b7d22d92e285308be8c114ffa5887bf3be0bf4c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59cf7db0eead3c13e358c6914e26d5128c90c98f9c72406f37ad1b0832396c3 +size 744990 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..effcb2464953e72ab1cf8351b611b26969badb59 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f75ccbe5415a3bf4126696c9a686960eef46f097aba02031461711ae474fbc +size 1997824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a66a23f5f8ef2aa3912d178dfedf2035ff37c0e1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a49b12b082ce2bdd4394+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ccc971d29fb445fb7a519fdbef9850ec9cfbacaa6c2b3bce66863da44c68c2 +size 2169547 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ad318adeea5245c4996f34feeb996e730d73860 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7892682093f8c05f27aa5252a5e0acadab1182cd93f390fa41e36d04fe2abf8b +size 79742 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3b8cf66f8400de5a681bbbbd5c0f49daed98808b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b27452317f920f720aebd337b496affde238240b9835d912b023ac0a418276 +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..72e3485383f041729d645713dfe7261c0661c096 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5547eb46e421a4d941c47f4623b4bee25fcd4248a01a1e6b709457b964b1326 +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..622ad1b68e49ff6ea936e0013ea8cb4aac059ced --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a72f28e668e46cd358e14bd7129f7fbeb247f20244f75febfce5cd0658932f0 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..089d2fe0f250f49558924ccb8fdf25d122a634bd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b6e95760b38f249119c0916517c0021346d8c7908b5566fffa0ccb5067cd11 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..984341981bd30dd232c0319ff89f31b759c67b25 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c89125b142930ed35d0a42a451fcc789e56fcbd5e42e583366be9ce77d6491f +size 1070647 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..62c08c0dcf65c3a657bc6761c5570bb4d2599e37 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3943a35d4a79c83f1ae10ba16c0785b81d73494ad9f043f5c51ae1e6ccb160ea +size 4998144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7d3ff5c29bcdcf392e80bd46f9e323f37b752710 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9b761f317f27ca2c845+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f06dfa5266a83fea6bc8becedc14e5393fd3765894bb33dcbb1381dc870cc22 +size 5171427 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d1075191777ba214126eb790cc22dcc1707e5550 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0cb39871d10aadcbb4be93e916b68466fa74111337612de5f3949208542fc4 +size 92962 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb.lock b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb.lock new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..76102661e28b8fa2b7042c6b4336c1d62fbd85b4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd97a5178f1294bcc60c1a3a853d5892aa2f834138a2cb73035a98c01302618 +size 339944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c02649911b7bb1a002faad4da699504a3b8c8dba --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_abffbaee6c01c4e3d2c4+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922850e7a45fe1ebd7ba3df3ecd0e7f8febf582c9c538e7e78cf7afe20a4f645 +size 7711744 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0abb03e6ba3f71a70a8824f68651776088c5d896 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5b9644aac04a3d73164009caaa0f9efa04f8817148b75a22e9702911e0e6b0 +size 52490 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b778828cb6ad4cadde8bf59112fc9c7c72670df5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08baa04ac2ec2bcfe37d17bca836289f71f07c92a38220c09580b366f569df41 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9c23a6c4af4d7f645c369413675fc01f8e8f7ed3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950226e7cca1d7365271ddd73b1095b0ff05c437165a8fd5e20deb8b165a63e5 +size 195507 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d7470aed79d91cfa86f4f98fcaed3980077956fc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21988309ab35c792ff07095595756d5704884e71a5b0cdc3b7f38f42939190d +size 745398 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2d502fcdb8c182c0cc9bcb18644c70a8397a544c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735b085988e657797e4baa665bb99948a76f80f479c231e06baa536dca53f266 +size 3083264 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5d5a53f2adf2b11983697cff479d2db12f14c91e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b19bd1cae910012a5fa6+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247da6fe93a0c8e1d0d534ef5141d56dc23cde617f9b4231c3fdea1f67e523a4 +size 3254990 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fca2f7f1b0ed3cac95ebc7e495f4caffff3a496b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8a0a7013c110b44aaaec4b50cae1e5959e1913beb3ea2335d8adbb455acfa5 +size 576230 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ffd9432ccb8b448b3edc8fae5fffd501c107267e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99b5e875fc8436e3e28b9aa4eab699c40bfe177c512cf00b8642f94c9cf0995 +size 1455104 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..27daa0ea1aa2faa26612044f80f53b7ba883f5e9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a24fdc65289021b8b6e1a20c0e107d16bd3cecc62faded4b1a06ddc1235f51 +size 1600015 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5c198c977e9ea4944d4dbb3d89a549ea06998dcf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cc6faf99551296c87aed865cf33e7b5d9d680545b16bdc0af35824a6cbc7ed +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d46517079276a4dab359811006e2ef767e591b47 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3922fb6a70df3e2474d+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c93da2b0f65324f182111345b86306629d670847120811323a5e36111f4b7a +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..910fd42341c7a91026feff8e73bcb6563572229f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec344eaf4f9b146d749fadc8eb5f88bfbf8405f8e64c52e2610b0c71e684c97 +size 2327880 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f20a2894c779d49ad3d7f2a604faf7996c184d43 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b3972df3e33231af7683+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f15eceed7c2c2faead9e79476187e1a2bf97e85c98989781e687d6217daaa9 +size 3390464 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bbd39f65dce3a32962495fd3940a4bb22bbe0813 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3efd264fa85cc5d8470175003fb874262c6b4b70a263349a61a2799de8165e7 +size 80360 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..99b3e58c9c090eb2917759f26ce12f0d306cce56 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965983486c0c70da0656edbaf785f28048536f0b87652feb42296e05745c8c84 +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..12b825d138eaf5975633b727994b863acdc1eb9c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b48fab2b0df2acb937c8+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ced6b0953720323cad5bd107ba88d595adde8034789e47222f35025179bb8ac +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2126e7612ab803400fe642b391d49f5d6bcd1464 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9958c7d5f720b797c18b96c49efd066e29ec798196fccc80c344806841aea66d +size 415162 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..aca14539804f206fbd228a8b100b7570a87f900e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f7416533727b1fa0d82acbb80380a8156a7a8e53fe897f87fb3a7d309410fe +size 2694144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b4e6c16f42b5841a3b416a34149ff1004ecb23d9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e4287bfc92bf850eea4d10461af2352f2edc23a29ebe6782591e1b850f075f +size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5c576b737d9ff722a68ce0d0067e30e98e735637 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284a5071c265c48612d234ce96a5c2855f346de8b297018766db228865277ee9 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a05db28aa1daa64e1e6adf1788a0b8c7cdbbe8bf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700fdb2999174103945b216119818f393e43318102778ceea42408cea535ef67 +size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5bd62aa52442ddca10951bfc79c87e8e11226db7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57afc6cfa83683d461e4e7a29bf91aa41b051b845bab370323414a6a7ec44a6d +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..92aab4de6e655e40a4edf39f10cf845d8a241029 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3af38dc3759a0077763bc94bddf02381e1b81d210fb62517f722b06bfc5683 +size 44058 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f0ad67ca06668adfbd0292f90c3ee8f2b47f9816 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42979cd0ec9a5f3294698a306d1083ffe6c98f8a98fe89bc2760dfab9097396c +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b248385fe494ffc7cad59a16508e903029cff1d6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ee20aa4f1f1686fd0bf72fcbb970e56e5afd7f78ff60bcfed24affa4a8fb80 +size 193010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e5429c3c1bfea143c0553c0c5b99573952190748 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38fd4d07237114f1e5b7b152b9ecc9e7faed11bd73abc539f18a609261d2fcc2 +size 1911064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8b4f28026983fd4fe77b23cefbc7cd306f7fe8f1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd9b5e25d91bca9370d52607a23e2e1e2888ddf185e2809c4d075ebc16a6724 +size 9944064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b33048b2c0e28fc431a271dcdb143f56c1adc1c9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bcadb50ab85e2fba8d71+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99de851664d7db2ffcf1ddd5a51897a67461dca7912bed4cb5becfd72f45f322 +size 10287639 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6bdc9b3f6c2cb319581f335e4fc003bfe1552f1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e822cc0103b48f977d51f21735919ceff3c97ad01acc5e6b5736a90686d2b0a +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f4a6fef7bd810b632024396139850a529a70e31d Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..39174d7dd5530fffae9e3cf826973d855720c57f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9f7682a68adc61d2363757bcf548c22a5f8b5a3bbe768fda1e8b80b7ca34d8 +size 944123 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fdbe243a82f26ebd87a6bda311deabf7164cc2d1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bf2b84c02a9cc5486e3e+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212eecc57bff1679126e3bf0b125d0dbfa9f17ef653f818ced0553e11cbdf586 +size 31140864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7082181dde36b2061da7b16bac0f29aa8bfff740 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d84a277863d35907d662445efb1df12c4f6a5c3d14f4527ddd3a12e12e2a0c1a +size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c0517df02caba50d79cdacb6b2fcba2e548570ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13df5caee314b6b48ab7b6b54cce95a9671e62bbc61ae60da8147c79df333119 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e86b6b5bd3a002008976aaee568fc57d8363e111 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3cc9f83f80d94830a254502de2641b637f314d2443dc11e2df3d9febb57c81f +size 88894 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..804e207e2418e3f4545d81d6c5531911c6bcbabe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b633e19f1762738f127621ff50d126405e0aea355b8abadbba521b3a4adcf4 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..be98b35c896f791f6941cda19904560394773a3d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e64ac581f0a7cf925adea4b412b0e40d764dcb011500119d451cd986f5d4eb +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fca2f7f1b0ed3cac95ebc7e495f4caffff3a496b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8a0a7013c110b44aaaec4b50cae1e5959e1913beb3ea2335d8adbb455acfa5 +size 576230 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..832972d50cd1bd483f0ac100d05f950640206db6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a555f689bfb06d2ac007bbce46b2beb6d12fab2188c73a9387040d78d649c6d7 +size 1455104 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b0e1dacd0854d177e1b1e2ef97a8643c3922b40f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c4db0300d76c7be4ad13+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce74e773f706f280d7b14e50a400d4c4ad21c2aa78ddedf5e68887c249260f1 +size 1600015 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..97c8e29d3bf5e3fd6600e140c11a716b0a047e9c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4023d2c4fcfe210f7e7bf12f13b81ecc071eebfc958003de7f2019f4a46569e2 +size 1095125 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..254b4d5758463f859280b44471b17b0c07d895c3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1503c163901140c3c6cff34a88574d3b16f0cfcf93e5776aa6138f4c5d31702b +size 4885504 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..53e1d10bcf467986e7fc1de78f4ff805d2856a38 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c58c3b1c9745cdc8b7c7+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5267323fe94c9128dfe2dd422429248faff4e302101e83bb92f78c0cf7fd74c +size 5058549 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d4efb6a62361bb4fca80ece8c5e3b792ea9bfd3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ec8adc0e62d42819e2e31a593d500e4ecc872b5b66fad58c6413dcecc02964 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..767e39df75cf987f95ced701327516d637a88c27 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88035493eb87f34b119a4665d937e6a27e17a714 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e74f6e05b9bd84d59addc9f34ab7eef94e63734f2f1114b01407379ab01ac4 +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f6c9c6a98043d9e583d7703d88c6b5e9129fc399 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8046a8a7f9ad6384031b0159e58fb02705b802e7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53bfea1678237d2b5924073b1efd75949c3c18177e09b3ebb6df681d339534fc +size 11183 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a285e44091f4f3bbc8d49931ab201fa4d026961a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec637d13ae4a67a408500c92cc3626326d8479846f95ba2c07aa5eef08556c77 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..768d60a4d551453a1a7a9f5f4b0225c45cd78556 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4949c3d5a68f0516e9b23e07f97a659a019e4604259d3644eb220ca01c8e881 +size 387278 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9c3abcd4b1116e32c1e8b91daaab7543c1bee18f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4492649f3ff048845468a54a5c5784fef7a4dc5f56df87f811e1db00990653ba +size 31878144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..22dcf0f8c79ea418cd5ca2568a4ae6f6315ccc56 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8919938a040060bd5077eef2dfa9d7707e8483b155a3cc2449f75b6e5ccf99f7 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96d2fd66b7b404052a3f52202f94fe5485d46ebc Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..29142b934dadcb7bcc3f2122a9dea8385a4aaa1d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6682084cf0c3e57c3b8afdc5ee36c89117dc3ab7c7f93b5413fea8fad47d2f6e +size 740495 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..83e62a3e9a863727a8f23024915b028a9e557926 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db779cc7379d4872184a68b689b766da5fa55f7d3652a427b8f8b6cd712a6140 +size 2632704 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b51b9b1035d03ee93b7b2a92eed464a61a5359ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ccbf8bb7df972e5cced8+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776698576d8cf485df0deb15c6a7f6c5e8081d0b28acb152766a13da37a87de2 +size 2763248 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..30d121c538ad4cc92d45d7577dce9d46de0b9e53 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef13b886f0f2c3a85d82e75bf057f79daf13e03edf11f83c8ba652d4866f5ef +size 385134 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f873d0e19407cca45f6b19c609f413dd39372b57 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c81b3204ab5b0f437eb9ffb073d99229c72ec5f7e4185a891bfdc8e767b285c +size 31867904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2c5fcdff9fbfa35b7d64f748cbb7207bbcbe6ffa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0cd76ace5e6f1a3df1193b16ac13dc0b6c893919326dadab8f4c9c2e702b50c +size 1911064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7c12909a82ab224ab2b0684417b140d2dc940084 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b907ab33b50f4f3d212d6499b5144bb73a30d3c6c4888505dfd28886c0677952 +size 8233984 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fe1a536c8a9e846245b917f73b52f4dd1df0187c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d265ad478c2b4276dbcc+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e34beea364bce7e13b6ec51555ce7b79cd692014e00032cc5100e4ff1c63332 +size 8577559 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..591d4e4dda51ecec21b1b75673ee073e8caff458 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaed074a871abda3534bd7dd3b5dd4779494126d30f97103484e18cb4cb3ebbe +size 727029 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..76d0c68f47fdbdc522a1fbc5422eee94c234b4bf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0aa51c134553abece7312f57809757a411f5a357d2925104c3b76ab96acbeb +size 2714624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..352432de3d0fa604de467afae1ba8b10315137b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d366fd0dd6583a46a379+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54be03841656366ab3cac3e79074c2dc0dd5bb7c5f00990a8b61781f38618f78 +size 2884084 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ac9fd86642d5f71a7c71390bbed0da9fd2ff7ce2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63dd2bfc475da2d4b00f8437715534d80621de0f85409bafcb555854c689c198 +size 88449 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b70b213594d51fb31ee58c3c144a039a80934ced --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb62e966910e6b8ba39feae7c2c41c9f6c5b40f3988ccca499b229c9c6625453 +size 1178624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9c74f483559fdc81893ce15a2c0a9fb80881201a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f54913e8a38be19784fc08f94a57846677f6300bbc16748133894322a64cfc9 +size 79198 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2d43f71f7fbeffaa6ff9deaf124ee62df29ba049 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1ebf710d7cc5b0de84ef8e7920dcd8eb62252bec30e4f2e0da985dd31de9c7 +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7c4d2866082836642c5ba9e5cfcfe24ebb8cf7d6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42680fa0b68c035ecba291608b9ee78d9dce3a1d8932fe01a4eae9bf2d77e4f +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fdb550589a2fa7ed36d0199c63e7717572e6a727 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393a49d6d90cd37009cf8c73c3b76e9a655c04f4bdf378f2837f3c980e95b24d +size 902609 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..225cd655b9bee3ecc75d83f5ed7f615fbb382ace --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02759b5d7ce350ad085ddf8bd995b4cba09dac33c78c99c68e5652f7f7e03e5 +size 7506944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..12c9d702c96d2d3d5d79fcd0da25323e8071ccff --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c4bfb4a3a80783b2a17c61e627c81e514f5fd14b92ec0d4f5e601794825129 +size 773049 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..71b0d375a8ec791470e24c48ed1280a02929c2f4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a07eee4f4ad79222aac0a031687e6f074f85e939e3c6a0a73a761f23dfb7509 +size 3841024 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f53210580e7ca168dfcd6194ab25754d3eaff686 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d51b8cc19b9784687709+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6fc751ec3a222237c1b39a9c068244dfb1b597cd10c9f00f0a2a61d8f841fb +size 3978841 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5cda18a54ea6b4609b8f59466ae0bcff0c006b94 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a356c9353b7020234d28466ec3cb5c39c393e6b10a912b8614b530eaba30ba +size 84819 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..00576ee01014e912b0e43e551a16291943807564 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d52a1641563510c8105f+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99d550862bd38fa567722e6cf9e7ad4672d289f508fcb3debf2b5a71408b224 +size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..786cd81e8f21bf78f9abce1ea47eaa8ab4fec8b5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2beccd1fd50dfadce7099ef6bcb49aacb763e7a46f7a2c08985eb849212a2398 +size 80877 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9f274403448dff2f976921c99cd15d8945f82784 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00addaafb9ae272c100ae60700c2350525b8457ea84f9a3e5c0165aa00f2153a +size 308224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..dcf8d4c244627fc62922d99d4bdf24d368735a6e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c1782778ad3b04403e97bd62bc1748aa77b08d86e5fc513555288b28d4c4bc +size 319522 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ffee70cbee83d12ef55567d18ac2f1cf7fec84fa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c0186233e1e8fd262423a787edf1f033c3e1920648cac218a2b922f9731f08 +size 11183 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d67d9acd6b2a6fbe231449b40669f6c331329d37 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12baa0e6a5c8ae2d90ebf56eaa45a53f8085068dc450b5613927eafcad8e1350 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b1caea21590deaa14a822f7856781522a3db400f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1fc0df5d72d2bf09561d3762172af840ee9d87204f82ec8eb125258a3366af +size 81196 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df44b9fbc9079926bb767198f0e0157a0f85e6a7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8959e5ba74bbef101af07215c63952b1b5764bf88f0417a46805536c588c7525 +size 615424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..de577301d926c7401f0ee001fa14584320e82e42 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d757f0d340c8bb449f21+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfea7034c05bc2f266c3782e1bc2fc5399022784e8e9ef5be410d5cc665c4f0 +size 623263 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5f147dd1be539b023212ad611bc29974c4c4e0fe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa1f1c8aa58964fa1c21d32c9f6b27235496ca5a3c5b0971eef05f395e17244 +size 374859 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..039a66e561ea3ef85fc422e11159c84552cbd1ef --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90011a7b74cd8cedd21beab5f0105b67a975dcd1c99a509a7b76832aa6c4c8ae +size 2151424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..110a46367a74635e4f2ec80e2b4eb234e05c4d8a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930529517954a020d452a7d3cb9ec3fc249379cf44b05340e8a7e2993dad6a19 +size 2221053 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9cf2045169d9b050b22fc1bb51b9ecfff81b6862 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0472f8f74661777bc1504d1d0dba1094b30465f50bae9576a15449640ab51dab +size 172361 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6de944c18cafd39bdba5e04d8a922a82412fed84 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d84f59502564753faaf1+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6879d6759e2fd04da1faf21f3b48689a6aff0a67926deed21a47bdada119584e +size 2274304 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aa7a4fb4568bc565e27acfe799a5de85457d36db --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6d5a5be9919a74ed98e393173a78348c9b7a39dc5bd0a6d00394299fddaafc +size 174784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c872d21e0608be2508b871ed53abd2bac7e6ffd2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d88489730602114d4d35+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a379d77e3a1b79322fc4aced7a969a9cbd9cbef2e53302b7f8b7f7cb787dc48 +size 1711104 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5dfc031cbfc50005e9ab3569c0954fbad0e1f3de --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b4d819deb1de11993c4781088e8cd90b8ec691f7a4bcb00c0c1c257947c246 +size 69179 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..63d3a49485f4766ae4f97ac71cffee3dc827081c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7614258fc592bd21a671fc29fd833fdf6321eab9923b28bdaa281a03ea028aa0 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b72fd7079202294281d082b853096297c8c1f04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0652c2837255ddb07aee5fdffebf5b8ae68da37845f1e83aabe3f152b2b40db6 +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e493d501dab7626cee2a41ac607c678ad06bdb44 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07320203e12321430e926d11e45f841c5dada2dcdc4b9494ef6ce64d5ae37a6c +size 858046 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bb35d5f9d0236fba65cfbcaa32dbd3b2ab97c1c1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_db708956da7a3174471d+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070af26c182dbd87738d25306473305a2e2e20171fdf6d04bcbfc2fdab5ffa43 +size 5786624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a98599b55141de014460bad9ba04aacd70cf50cd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3a7645ddeedb3273fe4c6af527eb3cbb7b5777bd4226d638f5c11695c01d27 +size 718732 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..845218681b7932a6468e7169efe72b28f8ddbfbd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dc2d595d0dd94ca21077+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b2a63dcaffa39c0e822041e63e1a7bf24c28c3c41d8602eb06d8d0913f10bd +size 19835904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b8a9679d389721fe5e0b7e823b10ef0e15f4dcd5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf230a29d7c5746f640a9b189af232ed164e806cb1accaefe12c42979cc1673 +size 900724 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f8c74c7c17b62eacfd5b43a3732e6406835bf44d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_dcf9688803fac8be3bc6+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8988d792d050311cca8b32114e026df9b6bc8cfdb6c0bfe28ab8d2572da1744 +size 5817344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eec7fed12e5600f29e00498508c27ddc56b7a787 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffa79e252b3ab5a178f15d5680b162a5ff48ece318bf95a4122231f100bd639 +size 149912 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7ad88fc9e26890d00987e59616603c6d6a0420f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_de463290b0cc81f3e50a+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3848fcec9b32af2021ea06f33bd5924122b55f43a41b7fe1e76d97d0215fa4c8 +size 594944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..107cebd2dc9223d7d557c2256bdd494131263beb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b25ba34ceb75e44194415a1b72bd90707c39db39 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f599ce69d962eb886127c2db10ab5c5dacd77051234269877f5c8ad84f473e +size 745398 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..248fcf23f3275f35cd1731ca59683a829e917d0d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7305d37ac4aede1368287e2e62ba519682ba1e3cf145273ff960470a8b342aab +size 2468864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..05a9eee8435fd128edab04f75392b92d11bb6f07 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e09b62be1d6d8ad18632+617f6939/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74d67e1562716284c3832f66d415f62749f6b3c57322035535309f16d579e4c +size 2640590 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5bf0b713326be46226d73cc9c32ac27ab28e37ad --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c5db0309eddcc2c3313b025fa81c4f09d88c3f03eb3d861f21d6753dab4b9b +size 136006 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d5d8d9250ab0f9d4e126dbee0d13c0dbe37b71b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e39dff68d617900c6e31+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6634231278b54f98f297f928eaf2ee3e55b150ea5cb416f9e81bf2a27085d323 +size 3974144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..68aa30e43cfbef54a9968bc017dc327c2d7d2bce --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee70ecbac589b9d810beecbc33403025e0a508fbd6e1da5a4a39e153dae8c79 +size 10010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d036bf54791b2823581ae8969bb072d651a1e6b6 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8a554e1b77b9a7df908fa74bdc87045aa82e3fae --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff9d6f42eae55702201bb0e47eb34ec59feb160a18d9cd679c5a34266c5256d +size 339944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..26053178883b79c7517ec4744b80fee78620c017 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4125c11885b90ff94c9+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c1b555dfee8836335340f096cf1e165c95afdcf6b22edca04d598dfa2053988 +size 8182784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3bfe984fcdc978e129c8ea5b82b56a969aa19f82 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90219bf03934f40c0c8753f2e706536d262abb06db039f0e806a238e39b6a3d3 +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2c0bd2f7e7c2545669b56b69754c921dad93cff3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e48df5a1ca8b2b49e13f+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b909a79a3a657d1ff90463f00c789bc37a5f0f958d50f7128eae8ea05697051 +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b45c639e4a7e818e4d96f69f71149d19b10389fb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb25c443d6cf2fe2e2ab55b05029569a1aa3e75608c0634a8650533b06c46b4 +size 46622 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9e203f494f922b8f4690c863f764105ccdf6534f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23194ec69f19c8f3023e75314b47e31e462b52c4e3ad5482c7c5871a4fce399b +size 144384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9cbbc4c635ad7641dfda536147ede80bccdcfb89 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1606fd12d57efa1a8823b5f6cebc151cbe7fabf201a575f62206bebe1d973e +size 715372 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dd6e80c40c08f1909407b70c00598082e7476ad9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e6cf0fcd9a16a4306e4c+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8875e6a1fdad78dafd4d4808f2ef48525c34c0f1b30f6af4cb1743c8d30e82 +size 19835904 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e08ab2a017ede610ee2080d0613c125fdfb26d15 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4783d95ce482fde3ff7fbc5324c1ed7863c13430bfe5fb2c7e2b63d12d4d72e +size 567258 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9b38714c7e8d688f768725d33bca7cf7c3f0f645 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e716cefc11279f5393c2+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0025889e1d2f74e920d20550648f63d41cad29aa66d3f55d5a5dae05cc65254b +size 1137664 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f524b4d84fcccd213f4128939be74a9bb7db75a3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48412c7154ef9caf74e2899d90a4085240ce0ca00aba12c66d03ad68033ea9b6 +size 1072456 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a135d406d3045179c928535e4aca9ac60a39efc7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314b16eba4c33e383a5ac51d528eb9606d541d293120e6900709cdaa72b448c7 +size 6605824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..14baac76b252c4f5619625e0bb51aa8bcef52a52 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4135cdf3a474d12793ab55474180091c957ef032abef7de650b0a277cb2048f +size 47478 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..83b0124ec96368bc29408c631698f5485dd1a727 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6c609b2232870f2babcf7c062f4312c306563a2d58f3f7cc7589af54486206 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e1b654f7aa1b236f61ce11d4d2d7def510af33fc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed49b3652b4f42ce57d1c568c4c3ec3323477cc0f5a45743b3aa2c5f69ac0f38 +size 740826 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5c1b200a85035aa8d2f7b5d1b5ad313171c912e0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f9636be6419181ac51065f002e831f94d1fddecb8fdb1978c660bbc20ed9ac +size 7384064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..dbf377ba5dd801ebe2b862e6e3a10f9076ab9832 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312f3025d6c150205d408ca4e813c23f92ac17c47b9d403c6e8e118e7c670bb9 +size 7578631 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b0c85d9696dec1152ed8b6226f220ef5f04e99dc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f24cf0e2fd4165cbc72aaa296d6ddbe5aa7a5fc2932438037e6e6756d17c79 +size 79742 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c706e0e2f788091940e1e6fb29fee10bcc581c03 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5e2613d1545896183e46759da4737705fa3052496c2c0aa4ddb37bbb2107cf +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e8572650f209247da9303c684b5871cbc820adad --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c21acc33f6e60cbda5020f093f53dc890646c0446c4b7c881d3b597d970e18 +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48c060bfc566a2808b5ac053f2c6154a586b957f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce55f9f3b779172d357a166157f85e849aef70cc86fc56962d5dd729022e4b4 +size 773433 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f3e3f12d2391de22aadf092dfaaa037fc832ff68 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6969e3652e9d4c9605bb9b538e7467a7e51bd5ceba9981fb92784f0e28f225b +size 6237184 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cfd28983eb686b722181e3b5f0d7587f7d0c4e91 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_eb35938cbfc781930141+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05205d1e0412418e6181ac619583bccd7ee5278736b7c9e959c32a236245b46f +size 6375001 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..91776ef5712b5571d1de1baff244a9c499834010 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffccba216823c3cebff446b9b6a9b9faa3fc2e76552e65e0df5499d0a03a273 +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d90108d89e43372f408f85c098fa8a88e6c1a0de --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ec3616cec65f8deb284b+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636bcd5261129fea69900483b03b798ec23da6207d24586bab57257550121d11 +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7ac17f6035702ed025e259a4ab0b6a66e7b9dac1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6adc0afbde64c61bc0c59d708742998d0ed8cacedd763d5b897f26939ef4e46 +size 7004 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3811d7917b56c964461723a18a924339eb13ffa9 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fb695bf04818e144ab11e8e4762675a8897016fa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13bfce5f8dce68177779e49abdf63276292c3a737e321b9d72e09389be145e3 +size 135999 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..08da78d525f1f719d5f8bfcec45e8a2d8257b4f0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ef8771b8447d48519ae4+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2897ded479757c09958822fc780197d52175739e8c36edd6403aa2df5bf5a1e2 +size 3974144 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ad722b76e0c92f11139d95322d0e4b8c64f7b933 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90b09fb4dd3cdfe0cfd6be83affe37b3d42d7cd5644fb220a51b2145b6e75d8f +size 88449 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7aa3afbfb6d25f3e5bcb147742b0ed5b1c211f52 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f101d5f6b79e47ea24cd+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3ab87f52d67ddded78138be2135b0830286157aabc64d3453ea73f7e2be11d +size 1178624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..58f4cb07f3acaee9b9ff560d4a8dd98c7c66196f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b086f89fdd83c753893ea4f9e290ae3ae7da3856dff528cc953936b24c590426 +size 427940 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..155ba5d163d42cc1e434103225ff618d1b6bffbe --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f407a744f5f40980a494+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75b500fc075523597f5bfd193d2c9e702baf6f46d03ce9798321e780b0cb123 +size 31120384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..132bc422001def92d60719e338da0d0394dd4954 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d1360974675cafa0d38921f0013c9df0c9639537b0d0076974f045646fa23e3 +size 773433 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..139ab3407aba884e4ca62946fa17a53e272a3469 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302a92c6f3fe621df127d000505e65a36912809c3216fadc23836a0cae7266e6 +size 4926464 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..19f565814dccb9b7cb99db680878ae0e37dd9d74 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f559b4b89708afc7e809+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236f5b7aba42341d1994d355b4f5bdeb2a0c816c819758d2b6e070f2ffffec6a +size 5064281 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5b857f4b4024797911985448ff7c2b6b2d07f5c6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac71ef9b4c634db790be9bc2da6cfe71b3b71bc0d838ef07283a2507070fe731 +size 53803 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2e9734edd1f01b2621c3e9d5f2cfc445ab01a1d1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a93567bf07e86174a5ca27805ac10d9b3ab71ce7296a78cf64add8ad31daec6 +size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5f0041db35a0a18aabd683fffe15804fbdfef132 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78cd1a927975c0c11ec88ee08db6cf99296abcaead1dbd17ee5c1b4515661b8c +size 85673 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d57ef5f3d55dc59958ff0bf486c3f7d23e0a563 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f80b15eb84a71eda0809+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:000b8223e20b07db367a808dc8cf0136ad7f23400becb18c8ff276dec8f3306c +size 328704 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b574e35656a698bf7d5f420f08ea7e890ccd7713 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24f6952bed3b510f10199c95e6a92ba54c483288f157c5f127a25187b9b1049 +size 149919 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..73acb4123e51cf306c881c6a43b358e42d803347 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988562484e328103e6a1144382a2e1f2406ee43963f03bcc068879224acb1cab +size 594944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2078b3647f01aa3165babe7ccfb751b4575e61 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4c7a25ec423eb9ecf78aaa32e5870966efd9e309 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f904043d81d836bd0374acd05de056e257e0d854b36af66b646aa6bcef23ff9 +size 1789812 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b65d1a7555d57fbb856abc6b859499a7c9d52f05 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8cade1575b9d31c15da+ad9e832d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b58e5f3568be6c98ea11334ac31a3b989f6ca4cb96275027ffc845199b1a1ab +size 2520064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..91cdde0a25ba1df9f098c32be00988e47cd7345d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339c23c9dc9b06cc18d3ddc6610dd04cf812c9cd2d347195b70f06454ce70ff7 +size 69177 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4237d3675e8adc880406ba92a59b454ebffd67c7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0257059d9e332b0a165601211a0f5a11c8471c1f55ea42fdf23e2fae04d278d +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c74a39bc36ecc53c7de6692932a6e7762b124356 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d618b554d92f95543e636879190f32bf698d8094c33e0a648cdff00e7a4e58b +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..405cdf51c8f199f5b762c1755ecf4f1f3ea92d6f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c82cceeac74db830842fc87d79de91a9ca79a9fd5b1729cffedbdf34daf6de6 +size 456914 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5bef89b9a8fd9e5dd118ada73f23f0770372b254 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f96d048ced77ea0c8420+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d749fe5c2828285063b9d212f496cad497c8103b280029a8fe2694451d3a7118 +size 31376384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c1ab58f32c71f1d32dee441b486f37f11dc3898e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9301197ab622d6cf7fc9b997b77ddb90e143075decfbd981455569f9c3a19328 +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1a2e1104a21396506c6792c4c114e2649a39ed55 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1f0f55a41a51a6eb581eb61a4aa6862881c6f70b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d355bd59f97b1c0a1f84eafdd160fcd75b76f140d64ab17d9160882192ce31 +size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..304e6c86edf180bcacd9375abeaec5eba0b8d848 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c583f05ab1185b65e73bb38a681cf39ff4378e229cdb17dbb5fe666a2b05f7a1 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..75c1c5e51d4b46cd7cf30b4c94537b0d053da739 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9ccb4fa5218da04f6761ff6e3c9da70a2b7aa93865dba648bf35f132f2c350 +size 149919 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b5d56556bc7123cf5f99295a5aaf0ffc2dfdf3f7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcbb78f6f5b1416b493a+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059f96389e036eb9cc3832b66c1e95456808eba6293b51b410f190522d869c29 +size 594944 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a89613e6a6025b4c0b2ad94030eb5d954b64ed0c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d0640d765132bd086a33e99d182e5d9a8aac851a83138e176a97317ed251aa +size 702501 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c60c7ed4c59b48d77794f82525223ffcfaa98f1f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965e436898344a1794a7485a6d22c9270a361cc0d1708fc79a009622a4f1024f +size 2612224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..881790075f7406b5325cde84193ff6c94f84d907 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b05680539419dadecda1725b6115918e24721e06b15bd7a0cef2d8306d1d09 +size 2742657 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..96f0f665e40bbd914c5329bae8672a3bc9702f12 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21bf8708e5b7b7b674bc3f8b59d8de802d7ba0a01f9e0c21b15c2507bb6d8fb0 +size 149912 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c164f0cd5521c8168500d3d5a6cb34fb7117c8b0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe5cc26344fc85d3582c+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691ff94896df2a2b408b2fcb75dd7550bfe913e8d113b6df2db51bae2f9edd3c +size 594944