Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
611
dacorvo HF Staff commited on
Commit
0441746
·
verified ·
1 Parent(s): d74a82a

Synchronizing local compiler cache.

Browse files
Files changed (29) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/lmsys/vicuna-7b-v1.5/e97cee8aebea02bd5bea.json +71 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb +1 -1
  4. neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff +1 -1
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/compile_flags.json +1 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.done +0 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.hlo_module.pb +3 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.neff +3 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/wrapped_neff.hlo +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff +1 -1
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo +1 -1
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb +1 -1
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff +1 -1
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/compile_flags.json +1 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.done +0 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.hlo_module.pb +3 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.neff +3 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/compile_flags.json +1 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.done +0 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.hlo_module.pb +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.neff +3 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff +1 -1
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo +1 -1
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff +1 -1
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo +1 -1
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb +1 -1
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff +1 -1
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff +1 -1
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo +1 -1
.gitattributes CHANGED
@@ -9595,3 +9595,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2ef05d97da42fea190ce+ed72d204/model.neff f
9595
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_67811caf6d2a11251332+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
9596
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_9adef94cb152fca0e97b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9597
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_9adef94cb152fca0e97b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
9595
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_67811caf6d2a11251332+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
9596
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_9adef94cb152fca0e97b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9597
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_9adef94cb152fca0e97b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
9598
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9599
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
9600
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
9601
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/lmsys/vicuna-7b-v1.5/e97cee8aebea02bd5bea.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "lmsys/vicuna-7b-v1.5",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "async_mode": false,
21
+ "attn_kernel_enabled": false,
22
+ "batch_size": 4,
23
+ "capacity_factor": null,
24
+ "cc_pipeline_tiling_factor": 2,
25
+ "checkpoint_id": "lmsys/vicuna-7b-v1.5",
26
+ "checkpoint_revision": "3321f76e3f527bd14065daf69dad9344000a201d",
27
+ "continuous_batching": true,
28
+ "enable_bucketing": false,
29
+ "ep_degree": 1,
30
+ "flash_decoding_enabled": false,
31
+ "fused_qkv": true,
32
+ "glu_mlp": true,
33
+ "is_chunked_prefill": false,
34
+ "local_ranks_size": 2,
35
+ "logical_nc_config": 1,
36
+ "max_batch_size": 4,
37
+ "max_context_length": 4096,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 4096,
42
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev5",
46
+ "output_logits": false,
47
+ "padding_side": "right",
48
+ "pp_degree": 1,
49
+ "qk_layernorm": false,
50
+ "qkv_kernel_enabled": false,
51
+ "rpl_reduce_dtype": "float16",
52
+ "sequence_length": 4096,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "float16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 32,
62
+ "num_hidden_layers": 32,
63
+ "num_key_value_heads": 32,
64
+ "pretraining_tp": 1,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": null,
67
+ "rope_theta": 10000.0,
68
+ "tie_word_embeddings": false,
69
+ "use_cache": true,
70
+ "vocab_size": 32000
71
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce8ab69c78f9087ad35e56c2f49ab70442de201a04a36e6c0557177a7165ec71
3
  size 947655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c399006b96346ddc3bbf6fb34b8fa58f83424b5569fa38ed694d74f5f6fffe8e
3
  size 947655
neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:206f0245d8735f1169a6a8bd482d3e9bc577903f4e9634beaa8c01b4af168750
3
  size 31130624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbc1dd3e64bb4f6a00bc022c66d0d94ee9f63c53c7ce14c6398210b61fd68d3
3
  size 31130624
neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
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"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421c0790bc999a276398a15f5132c8d0e5a6f5a9332126d72c030662c0e7e03a
3
+ size 692571
neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10fdfb2a9be184b1671773a138ecbdf8315dc112fecd405d378090378487aca2
3
+ size 11592704
neuronxcc-2.19.8089.0+8ab9f450/MODULE_19fb650ea0365a963bae+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95ed686bfb44b8fee470600d3d7dfc055315fc272892cd6ba0d14ce81250e09
3
+ size 11730534
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824e2d358a46e0c593ebe16d70ddc00a08bf3186c3a7a9670cc2f58e05aa5c42
3
  size 4946944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb0070af584295dd6285c8a81c9e2a23a2228afcd40aecb54cabf763d4a08b8
3
  size 4946944
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37fa2e5c594e7f4b0947d35e59a24754e7df7dda50abd661be92613cd2c33a5c
3
  size 5084761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980b08a3d585a5028932197799031d54a4f422dcad80fb0f422fa2e8a75f057e
3
  size 5084761
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee09cca30c07d9ea1951888ffe1b317eeb335d6879e9d9a4470f07b1105d87cc
3
  size 947655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344c4bc4f621e87f2aa6a2bbfaf4a6e25ec60f43ada7685289202fa2727383bf
3
  size 947655
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0567e22a05f623f75ca2fbee70a1a823dd90c5a34bd54a23ce0ad8dd76daee5e
3
  size 31130624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07c5df094dc0a3a2f756a022d4628e79090744a074901ef727ee1dd413e30f9
3
  size 31130624
neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+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-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee810c780b6f19ceb32bfa318b90123d49ae23fc64789f95b8afbca1a45f7d9
3
+ size 136028
neuronxcc-2.19.8089.0+8ab9f450/MODULE_709e27ea0837ab2ac29f+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40bfd77af9c7f8289def7bf48efad082f90dac5da5b0ad91a75c79be7970e12
3
+ size 5551104
neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
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"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8001e38901ffd6ad575a1074861b4c893ea572851726fdb4c229f2de2b1c15e2
3
+ size 904018
neuronxcc-2.19.8089.0+8ab9f450/MODULE_974b4eaebaec7a61e2db+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d211238483cbfa77dbafb5ca70c20ca466ed4d847f0f17b469c5e2fd370eb82
3
+ size 7046144
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b137e3e7e9461d21dae4b107a9d66542860e3ec5f0d9766890aa2c705fef9e1
3
  size 3144704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6d5deaa271b7ab28ec280f81564f0a1232b5ef2880e224c8cfdcf41ac2e155
3
  size 3144704
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c4faa0a5dcd29db15650b3f433c30d0743e07ea21103363a9efd6074fbb77c
3
  size 3282521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568a5bb90dec1dc6fe93fd30494297ac75353e840b26fc46e262e26dfcf33a4c
3
  size 3282521
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b6724b129b0e15a1e673b51eb5d54aeff8e3144f8454ff38d0d1e9db9b51af9
3
  size 2509824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81871f5818c5a8384da49c2a75ce03b059c7941ac1db1caf4e06cdf152dcf3c8
3
  size 2509824
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c525fea5f0439318b60a4000ca1900953b4067372cfa9d227b9cbf68a48be01
3
  size 2647641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48c7b70611073238308eefeb5e60494c998f16071b76bcb6c32a3854e6c3a38
3
  size 2647641
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd2bd03b7f66fad32a7ff8b73ce79dcf3f3fb1c0fe43738b0727a3f9795e5e9
3
  size 947655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052268bdd18341b626c017384e77add1212fc423ce025e12d4ba52e4426ff00b
3
  size 947655
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7324a3984c27b378f15f9b5d25582b13337e8c6e70f949037e632227d903a2b4
3
  size 31130624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d3732617b0128dd5398936a00cf986a8857e28585f52cb932db04df48ef57b
3
  size 31130624
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f83c4ed87974ffd31d164af2afe5004dd61d332e3a791d11b3450b67202b214
3
  size 3871744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6455505999f318298bd9c922db8446eb2945a0c2fcd7078851ee360653259b2
3
  size 3871744
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:382320cc53e615a1b32fbe2309839e198a1d90a8e99e5d186ef04d61060365a5
3
  size 4009561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940b761e425c43626c45170ed60dc175957d65c900eac43c9cbd5404d3c52fe3
3
  size 4009561