Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
tengomucho HF Staff commited on
Commit
1f65216
·
verified ·
1 Parent(s): 168dbd6

Synchronizing local compiler cache.

Browse files
Files changed (30) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/gpt_oss/plop-internal/pytorch-rc-20b/f051e27ac1b632f07897.json +110 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/compile_flags.json +1 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.done +0 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.hlo_module.pb +3 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.neff +3 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/wrapped_neff.hlo +3 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4060cec0b59c914ed674+ed72d204/compile_flags.json +1 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4060cec0b59c914ed674+ed72d204/model.hlo_module.pb +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4060cec0b59c914ed674+ed72d204/model.hlo_module.pb.lock +0 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/compile_flags.json +1 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.done +0 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.hlo_module.pb +3 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.neff +3 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/wrapped_neff.hlo +3 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ed1e4ca4ea70401ca1c+a9d440f5/model.neff +1 -1
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ed1e4ca4ea70401ca1c+a9d440f5/wrapped_neff.hlo +1 -1
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_54db317c5a291d140b86+a9d440f5/compile_flags.json +1 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_54db317c5a291d140b86+a9d440f5/model.hlo_module.pb +3 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_54db317c5a291d140b86+a9d440f5/model.log +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/compile_flags.json +1 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.done +0 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.hlo_module.pb +3 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.neff +3 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_b695d5cc0521af5a71d2+ed72d204/model.hlo_module.pb +1 -1
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_b695d5cc0521af5a71d2+ed72d204/model.log +1 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/compile_flags.json +1 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.done +0 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.hlo_module.pb +3 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.neff +3 -0
.gitattributes CHANGED
@@ -3794,3 +3794,9 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a77b5a8ad35912f824c+ca355898/model.neff f
3794
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a77b5a8ad35912f824c+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3795
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_cff2e57c257f3af50683+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3796
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcee18008378465b9ce4+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
3794
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a77b5a8ad35912f824c+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3795
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_cff2e57c257f3af50683+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3796
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_fcee18008378465b9ce4+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
3797
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3798
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3799
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3800
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3801
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3802
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/gpt_oss/plop-internal/pytorch-rc-20b/f051e27ac1b632f07897.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "plop-internal/pytorch-rc-20b",
4
+ "_task": "text-generation",
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "experts_per_token": 4,
8
+ "head_dim": 64,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2880,
11
+ "initial_context_length": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2880,
14
+ "layer_types": [
15
+ "sliding_attention",
16
+ "full_attention",
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "full_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 131072,
41
+ "mlp_bias": false,
42
+ "model_type": "gpt_oss",
43
+ "neuron": {
44
+ "_serialized_key": "NxDNeuronConfig",
45
+ "async_mode": false,
46
+ "attn_kernel_enabled": false,
47
+ "batch_size": 1,
48
+ "capacity_factor": null,
49
+ "cc_pipeline_tiling_factor": 2,
50
+ "checkpoint_id": "plop-internal/pytorch-rc-20b",
51
+ "checkpoint_revision": "76e3e2f0f869a387ebcecb73d98fba5a048c085a",
52
+ "continuous_batching": false,
53
+ "enable_bucketing": false,
54
+ "ep_degree": 1,
55
+ "flash_decoding_enabled": false,
56
+ "fused_qkv": false,
57
+ "glu_mlp": true,
58
+ "is_chunked_prefill": false,
59
+ "local_ranks_size": 16,
60
+ "logical_nc_config": 1,
61
+ "max_batch_size": 1,
62
+ "max_context_length": 4096,
63
+ "max_topk": 256,
64
+ "mlp_kernel_enabled": false,
65
+ "mlp_kernel_fuse_residual_add": false,
66
+ "n_active_tokens": 4096,
67
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
68
+ "num_cores_per_group": 1,
69
+ "on_device_sampling": false,
70
+ "optimum_neuron_version": "0.3.1.dev0",
71
+ "output_logits": false,
72
+ "padding_side": "right",
73
+ "pp_degree": 1,
74
+ "qk_layernorm": false,
75
+ "qkv_kernel_enabled": false,
76
+ "rpl_reduce_dtype": "bfloat16",
77
+ "sequence_length": 4096,
78
+ "sequence_parallel_enabled": false,
79
+ "speculation_length": 0,
80
+ "start_rank_id": 0,
81
+ "target": null,
82
+ "torch_dtype": "bfloat16",
83
+ "tp_degree": 16,
84
+ "vocab_parallel": false
85
+ },
86
+ "num_attention_heads": 64,
87
+ "num_experts": 32,
88
+ "num_experts_per_tok": 4,
89
+ "num_hidden_layers": 24,
90
+ "num_key_value_heads": 8,
91
+ "num_local_experts": 128,
92
+ "output_router_logits": false,
93
+ "rms_norm_eps": 1e-05,
94
+ "rope_ntk_alpha": 1,
95
+ "rope_ntk_beta": 32,
96
+ "rope_scaling": {
97
+ "beta_fast": 32.0,
98
+ "beta_slow": 1.0,
99
+ "factor": 32.0,
100
+ "rope_type": "yarn",
101
+ "truncate": false
102
+ },
103
+ "rope_scaling_factor": 32.0,
104
+ "rope_theta": 150000,
105
+ "router_aux_loss_coef": 0.9,
106
+ "sliding_window": 128,
107
+ "tie_word_embeddings": false,
108
+ "use_cache": true,
109
+ "vocab_size": 201088
110
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+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_0b4a867ac8ccc0adc30f+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7c1832c761a7c8b00370710f56458d46a586cbf934baf31d03782e856a6934
3
+ size 1012426
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d2428ec6a5a95d8346e81db66380c96a09dd4f573e9faf65ce560237ad7407
3
+ size 1700864
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b4a867ac8ccc0adc30f+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48397525b0015c7367c91d2ea2274582eb973ee3c49618a419290d94ace5a62e
3
+ size 1859903
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4060cec0b59c914ed674+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_4060cec0b59c914ed674+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66dffee7fa41d9ac57daa8ee15d81975c17fb7e3c8b646b8049d896cbf5a1054
3
+ size 255146202
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4060cec0b59c914ed674+ed72d204/model.hlo_module.pb.lock ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+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_41d38d9f3ba18a42f491+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab9fec342082f0a07414d31d72f47eabdd8cd802a6e568f47a64a2423532baf
3
+ size 971190
neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e67031915be4b0978f54ae0759ffca4825b5e541dea1f9f9895ca6abe684794
3
+ size 1434624
neuronxcc-2.19.8089.0+8ab9f450/MODULE_41d38d9f3ba18a42f491+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1994650842ee891a996296b4692fa1f2c4251812e2a2822fa09f54f6daa09d
3
+ size 1553815
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ed1e4ca4ea70401ca1c+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e890a716146d9a59af4da09e25f3d578e4354e38287ece0c077c2d7ac1621a9
3
  size 748544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d47b92669be6842cd9c1da3d600b7d21b63bc2e2910874ea1a32101a79f18b
3
  size 748544
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ed1e4ca4ea70401ca1c+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f5ba65cf7bb975a1835dd3098775dde405e5ab85c3e0bdf894b5f01cfb06df
3
  size 772992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6cc78f946f46795f8565376f97193c2ad1edbcd3685ec8cd98292cb036038a
3
  size 772992
neuronxcc-2.19.8089.0+8ab9f450/MODULE_54db317c5a291d140b86+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_54db317c5a291d140b86+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e39953ee935656200e7e725d5efb19396d76a0eeb7527317a9cb9a5b8de9ed
3
+ size 971087
neuronxcc-2.19.8089.0+8ab9f450/MODULE_54db317c5a291d140b86+a9d440f5/model.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_54db317c5a291d140b86+a9d440f5.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_54db317c5a291d140b86+a9d440f5.neff', '--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', '--verbose=35']: [XCG815] Estimated peak HBM usage (18.268820) exceeds 16GB. Neff won't be able to load on chip - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
2
+ 2025-08-01T20:46:50Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815] Estimated peak HBM usage (18.268820) exceeds 16GB. Neff won't be able to load on chip - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
3
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+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_6373bd891205842d16f2+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7570eefb8af74983a4e53df05cd115beec08dd1495915404cab31b64303a59b2
3
+ size 255331206
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6373bd891205842d16f2+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec37c2093b34f188a17578006ff60552569bf41a5569069fd8dc0ca19d206ae6
3
+ size 140862464
neuronxcc-2.19.8089.0+8ab9f450/MODULE_b695d5cc0521af5a71d2+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c17d50397e7f14e98ec7a192d28f00431bee79435138647151a044684d4e3da8
3
  size 40790698
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fdd0a28b51aede94ee64146624c6d123505cb5c5f67d5279671e9441277fec
3
  size 40790698
neuronxcc-2.19.8089.0+8ab9f450/MODULE_b695d5cc0521af5a71d2+ed72d204/model.log ADDED
@@ -0,0 +1 @@
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_b695d5cc0521af5a71d2+ed72d204.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_b695d5cc0521af5a71d2+ed72d204.neff', '--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', '--verbose=35']:
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+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_f8e9f8e2ab6f66f576c6+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b82d9097564c0a838d0c9e2e699762bfe5b69fb721972c06ead702b1da6979e
3
+ size 169252
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f8e9f8e2ab6f66f576c6+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2dd7459ff2363ff7276a69db8fe78a8118a1a900fbe01585f00ed688ca5f27a
3
+ size 779264