Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
474
dacorvo HF Staff commited on
Commit
30a0749
·
verified ·
1 Parent(s): dbb0edb

Synchronizing local compiler cache.

Browse files
Files changed (45) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-72B-Instruct/8cd3f0c94b036fce05ff.json +70 -0
  3. neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/compile_flags.json +1 -0
  4. neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.done +0 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.hlo_module.pb +3 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.neff +3 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_1c32f042ab25d2e73e4a+bfe5714b/compile_flags.json +1 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_1c32f042ab25d2e73e4a+bfe5714b/model.hlo_module.pb +3 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/compile_flags.json +1 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.done +0 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.hlo_module.pb +3 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.neff +3 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/wrapped_neff.hlo +3 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/compile_flags.json +1 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.done +0 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.hlo_module.pb +3 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.neff +3 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/wrapped_neff.hlo +3 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/compile_flags.json +1 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.done +0 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.hlo_module.pb +3 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.neff +3 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/wrapped_neff.hlo +3 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_64fe625d7455db65172b+bfe5714b/compile_flags.json +1 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_64fe625d7455db65172b+bfe5714b/model.hlo_module.pb +3 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_72a6e0e3f1105337028b+bfe5714b/compile_flags.json +1 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_72a6e0e3f1105337028b+bfe5714b/model.hlo_module.pb +3 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_7d247367bfe0eff40a8e+bfe5714b/compile_flags.json +1 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_7d247367bfe0eff40a8e+bfe5714b/model.hlo_module.pb +3 -0
  30. neuronxcc-2.17.194.0+d312836f/MODULE_ba6896aaaf0612ecd074+165e9558/compile_flags.json +1 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_ba6896aaaf0612ecd074+165e9558/model.hlo_module.pb +3 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/compile_flags.json +1 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.done +0 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.hlo_module.pb +3 -0
  35. neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.neff +3 -0
  36. neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/compile_flags.json +1 -0
  37. neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.done +0 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.hlo_module.pb +3 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.neff +3 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/wrapped_neff.hlo +3 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/compile_flags.json +1 -0
  42. neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.done +0 -0
  43. neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.hlo_module.pb +3 -0
  44. neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.neff +3 -0
  45. neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -8462,3 +8462,15 @@ neuronxcc-2.17.194.0+d312836f/MODULE_8341f89f99e9d3ed7317+165e9558/model.neff fi
8462
  neuronxcc-2.17.194.0+d312836f/MODULE_8341f89f99e9d3ed7317+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8463
  neuronxcc-2.17.194.0+d312836f/MODULE_d3dacc450634f2463c59+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8464
  neuronxcc-2.17.194.0+d312836f/MODULE_d3dacc450634f2463c59+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
8462
  neuronxcc-2.17.194.0+d312836f/MODULE_8341f89f99e9d3ed7317+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8463
  neuronxcc-2.17.194.0+d312836f/MODULE_d3dacc450634f2463c59+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8464
  neuronxcc-2.17.194.0+d312836f/MODULE_d3dacc450634f2463c59+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8465
+ neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
8466
+ neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8467
+ neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8468
+ neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8469
+ neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8470
+ neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8471
+ neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8472
+ neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
8473
+ neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8474
+ neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8475
+ neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8476
+ neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-72B-Instruct/8cd3f0c94b036fce05ff.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-72B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 29568,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct",
24
+ "checkpoint_revision": "495f39366efef23836d0cfae4fbe635880d2be31",
25
+ "continuous_batching": true,
26
+ "enable_bucketing": false,
27
+ "ep_degree": 1,
28
+ "flash_decoding_enabled": false,
29
+ "fused_qkv": false,
30
+ "glu_mlp": true,
31
+ "is_chunked_prefill": false,
32
+ "local_ranks_size": 24,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 4,
35
+ "max_context_length": 4096,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 4096,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev0",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 4096,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 24,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 64,
60
+ "num_hidden_layers": 80,
61
+ "num_key_value_heads": 8,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 131072,
66
+ "tie_word_embeddings": false,
67
+ "use_cache": true,
68
+ "use_sliding_window": false,
69
+ "vocab_size": 152064
70
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
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"
neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9440e5f4b6b2d53ce7368e70473a5cf24455b706c184857d3d07ef56e810fd
3
+ size 511803
neuronxcc-2.17.194.0+d312836f/MODULE_0f961aa4c3bad1c01e30+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcdff37cea8c4f7b93494851206edb1a4cedf0cb3c63c50e8bffd05c425d591
3
+ size 7855104
neuronxcc-2.17.194.0+d312836f/MODULE_1c32f042ab25d2e73e4a+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_1c32f042ab25d2e73e4a+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c4373b7c832b77b789f992f2bc3a9631dc27f4ee1bc8189c45f6d8025b5cb8
3
+ size 1974114
neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:550ebdc19c62a6072ae03d3cec3651e996d61aae15d65bb584430ddd0110b42b
3
+ size 2263557
neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e74f1ad3365065b002d0a49faab868c6020460b1331231eca3c45b26bb75d5e
3
+ size 10578944
neuronxcc-2.17.194.0+d312836f/MODULE_33763e14fe3354d44e1b+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b569dad3343a3f9486e34bef0bc1ff1245a89c29cc728fe041000f222859a76
3
+ size 11071618
neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7138a54c14e065557f64e07001d2ecef5924887fe0e529d41bc6e4e8ceefe4f
3
+ size 1795271
neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4485c26ff1f5d39a51557077f3e7f27d01e11c5e5eedcd814b52b8ec911f8348
3
+ size 6738944
neuronxcc-2.17.194.0+d312836f/MODULE_44321c66f9c2a00501e2+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbac23c0e566b116a318103302dedd7c95dca230f66d780958c4fc8cc525cb88
3
+ size 7134166
neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bd515b70c4eb565e9b5931163fcaa1a7b66881f8d76b4c4d495115a547b59d
3
+ size 1795271
neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925b153ed758aef16475ef94cf06e6cbc67d958f9e42eeb083097b6ed9a5c1e1
3
+ size 6738944
neuronxcc-2.17.194.0+d312836f/MODULE_459f6c7491e03760762a+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806eecf6cc3294e6e032faa78413c317c4a9c911a27e747838d8b6355b1bb5db
3
+ size 7134166
neuronxcc-2.17.194.0+d312836f/MODULE_64fe625d7455db65172b+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_64fe625d7455db65172b+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a038800d153224a4dd15fba8de2e7275ddc2177aa1d60f1ef64cdc7730c01408
3
+ size 2121288
neuronxcc-2.17.194.0+d312836f/MODULE_72a6e0e3f1105337028b+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_72a6e0e3f1105337028b+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5ce6c4001a2ea540df4386d733f61eb34aacb915dc3f8c74f55f00145e92de
3
+ size 1974114
neuronxcc-2.17.194.0+d312836f/MODULE_7d247367bfe0eff40a8e+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_7d247367bfe0eff40a8e+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b71f91d92f06301a86443e913a618b72efde87ebec30320b49ba8775f852a99
3
+ size 2121288
neuronxcc-2.17.194.0+d312836f/MODULE_ba6896aaaf0612ecd074+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_ba6896aaaf0612ecd074+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c5801d88fb0cadf93581c6fee16f5248ab6604ec7a35de726cc4887ff45791
3
+ size 2293034
neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7f5f5b7008aa904317a56ec68b1947c579b4decd3e35e29d9daad1d0948887
3
+ size 2662811
neuronxcc-2.17.194.0+d312836f/MODULE_baa132e68f25296780ed+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0607fbfd57d224fea4a0732b4d838ff662910750d4e59b88aaca44a316af667
3
+ size 4660224
neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49942f1f62cea79c92236e91bc3fb90562c3debba3efc41726eef3e3330f68a6
3
+ size 1800829
neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d577f153d7e997f2cdf4276d4d84b4dd37fbbe340bba06beacb4c3ed908c25f5
3
+ size 11746304
neuronxcc-2.17.194.0+d312836f/MODULE_df72eecd5fbe7225c6c9+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e184c79591759b4f496257a99a8efd91dfeda84e2b7a7e5addbbffb6bc93ed
3
+ size 12141649
neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--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"
neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c05d7006ce924cf18f0905715ec8df3733961cea0d7a128f94501b69c7ac79
3
+ size 1800829
neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9384b5530f319714beb63c027e907e301dd8f1dca074d77c71e39a297183e5d
3
+ size 11746304
neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed5fdb0ea8dc4fb43afced10a782bf4cbd7c898bc7cfb89d24bbd8375e7c96d
3
+ size 12141649