Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
tengomucho HF Staff commited on
Commit
fb84ba0
·
verified ·
1 Parent(s): f48f5ac

Synchronizing local compiler cache.

Browse files
Files changed (25) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/262dbf43da8b9b831afa.json +80 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/c5893ac2150961103e95.json +80 -0
  4. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/262dbf43da8b9b831afa.json +80 -0
  5. neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/compile_flags.json +1 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.done +0 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.hlo_module.pb +3 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.neff +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/compile_flags.json +1 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.done +0 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.hlo_module.pb +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.neff +3 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/wrapped_neff.hlo +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/compile_flags.json +1 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/model.hlo_module.pb +3 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/model.log +3 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/compile_flags.json +1 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.done +0 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.hlo_module.pb +3 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.neff +3 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/compile_flags.json +1 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.done +0 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.hlo_module.pb +3 -0
  24. neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.neff +3 -0
  25. neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -6314,3 +6314,9 @@ neuronxcc-2.21.33363.0+82129205/MODULE_9c01f09fb84f2b339fc6+fb4cc044/model.neff
6314
  neuronxcc-2.21.33363.0+82129205/MODULE_a08dd31a7a105fa45df2+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
6315
  neuronxcc-2.21.33363.0+82129205/MODULE_c913669652fcaa9d5638+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
6316
  neuronxcc-2.21.33363.0+82129205/MODULE_d3f277cf573c91b9ded8+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
6314
  neuronxcc-2.21.33363.0+82129205/MODULE_a08dd31a7a105fa45df2+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
6315
  neuronxcc-2.21.33363.0+82129205/MODULE_c913669652fcaa9d5638+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
6316
  neuronxcc-2.21.33363.0+82129205/MODULE_d3f277cf573c91b9ded8+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
6317
+ neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
6318
+ neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6319
+ neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6320
+ neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
6321
+ neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6322
+ neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/262dbf43da8b9b831afa.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "google/gemma-3-270m-it",
4
+ "_sliding_window_pattern": 6,
5
+ "_task": "text-generation",
6
+ "architectures": [
7
+ "Gemma3ForCausalLM"
8
+ ],
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_logit_softcapping": null,
12
+ "dtype": "bfloat16",
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 640,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2048,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "model_type": "gemma3_text",
41
+ "neuron": {
42
+ "_serialized_key": "NxDNeuronConfig",
43
+ "batch_size": 1,
44
+ "capacity_factor": null,
45
+ "checkpoint_id": "google/gemma-3-270m-it",
46
+ "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
47
+ "continuous_batching": false,
48
+ "ep_degree": 1,
49
+ "fused_qkv": true,
50
+ "glu_mlp": true,
51
+ "local_ranks_size": 2,
52
+ "max_batch_size": 1,
53
+ "max_context_length": 1024,
54
+ "max_topk": 256,
55
+ "n_active_tokens": 1024,
56
+ "neuronxcc_version": "2.21.33363.0+82129205",
57
+ "on_device_sampling": true,
58
+ "optimum_neuron_version": "0.4.5.dev2",
59
+ "output_logits": false,
60
+ "pp_degree": 1,
61
+ "sequence_length": 1024,
62
+ "speculation_length": 0,
63
+ "start_rank_id": 0,
64
+ "target": "trn2",
65
+ "torch_dtype": "bfloat16",
66
+ "tp_degree": 2
67
+ },
68
+ "num_attention_heads": 4,
69
+ "num_hidden_layers": 18,
70
+ "num_key_value_heads": 1,
71
+ "query_pre_attn_scalar": 256,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_local_base_freq": 10000.0,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 512,
77
+ "use_bidirectional_attention": false,
78
+ "use_cache": true,
79
+ "vocab_size": 262144
80
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/c5893ac2150961103e95.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "google/gemma-3-270m-it",
4
+ "_sliding_window_pattern": 6,
5
+ "_task": "text-generation",
6
+ "architectures": [
7
+ "Gemma3ForCausalLM"
8
+ ],
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_logit_softcapping": null,
12
+ "dtype": "bfloat16",
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 640,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2048,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "model_type": "gemma3_text",
41
+ "neuron": {
42
+ "_serialized_key": "NxDNeuronConfig",
43
+ "batch_size": 4,
44
+ "capacity_factor": null,
45
+ "checkpoint_id": "google/gemma-3-270m-it",
46
+ "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
47
+ "continuous_batching": true,
48
+ "ep_degree": 1,
49
+ "fused_qkv": true,
50
+ "glu_mlp": true,
51
+ "local_ranks_size": 4,
52
+ "max_batch_size": 4,
53
+ "max_context_length": 4096,
54
+ "max_topk": 256,
55
+ "n_active_tokens": 4096,
56
+ "neuronxcc_version": "2.21.33363.0+82129205",
57
+ "on_device_sampling": true,
58
+ "optimum_neuron_version": "0.4.5.dev2",
59
+ "output_logits": false,
60
+ "pp_degree": 1,
61
+ "sequence_length": 4096,
62
+ "speculation_length": 0,
63
+ "start_rank_id": 0,
64
+ "target": "trn2",
65
+ "torch_dtype": "bfloat16",
66
+ "tp_degree": 4
67
+ },
68
+ "num_attention_heads": 4,
69
+ "num_hidden_layers": 18,
70
+ "num_key_value_heads": 1,
71
+ "query_pre_attn_scalar": 256,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_local_base_freq": 10000.0,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 512,
77
+ "use_bidirectional_attention": false,
78
+ "use_cache": true,
79
+ "vocab_size": 262144
80
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/262dbf43da8b9b831afa.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "google/gemma-3-270m-it",
4
+ "_sliding_window_pattern": 6,
5
+ "_task": "text-generation",
6
+ "architectures": [
7
+ "Gemma3ForCausalLM"
8
+ ],
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_logit_softcapping": null,
12
+ "dtype": "bfloat16",
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 640,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2048,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "model_type": "gemma3_text",
41
+ "neuron": {
42
+ "_serialized_key": "NxDNeuronConfig",
43
+ "batch_size": 1,
44
+ "capacity_factor": null,
45
+ "checkpoint_id": "google/gemma-3-270m-it",
46
+ "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
47
+ "continuous_batching": false,
48
+ "ep_degree": 1,
49
+ "fused_qkv": true,
50
+ "glu_mlp": true,
51
+ "local_ranks_size": 2,
52
+ "max_batch_size": 1,
53
+ "max_context_length": 1024,
54
+ "max_topk": 256,
55
+ "n_active_tokens": 1024,
56
+ "neuronxcc_version": "2.21.33363.0+82129205",
57
+ "on_device_sampling": true,
58
+ "optimum_neuron_version": "0.4.5.dev2",
59
+ "output_logits": false,
60
+ "pp_degree": 1,
61
+ "sequence_length": 1024,
62
+ "speculation_length": 0,
63
+ "start_rank_id": 0,
64
+ "target": "trn2",
65
+ "torch_dtype": "bfloat16",
66
+ "tp_degree": 2
67
+ },
68
+ "num_attention_heads": 4,
69
+ "num_hidden_layers": 18,
70
+ "num_key_value_heads": 1,
71
+ "query_pre_attn_scalar": 256,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_local_base_freq": 10000.0,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 512,
77
+ "use_bidirectional_attention": false,
78
+ "use_cache": true,
79
+ "vocab_size": 262144
80
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ecd392051b643d9b4ba837b1c905ef4a770e5b3157285ec44589636f7063ee0
3
+ size 1751273
neuronxcc-2.21.33363.0+82129205/MODULE_1597528ce5f8288d7cad+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e8d71cae4d9e479650bf5e030437c43a358a85029b360213ecf586fe42e067
3
+ size 5786624
neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5f65d3906875ce7f16c7caca7c4385bdab56b87c06d2fa39f87e1b73e93c9e
3
+ size 2037253
neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dffe14040472ecfc9eddbca3ca522f46ce6d5a79053e2bee82325dfc3319e4
3
+ size 1659904
neuronxcc-2.21.33363.0+82129205/MODULE_2a860b864582fd3532df+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb56e6ad479df33e9b9e750dfc4231ee51715c2b91a63e9aaa4e9fb55dddb3d0
3
+ size 1782426
neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b35e15b9ba1f4059cb493698e4578bc9e9431923c70077626000989ad39fe8
3
+ size 1993762
neuronxcc-2.21.33363.0+82129205/MODULE_733566fd6dbe63a6b9ec+ac10809c/model.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_733566fd6dbe63a6b9ec+ac10809c.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_733566fd6dbe63a6b9ec+ac10809c.neff', '--target=trn2', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ', '-O2', '--lnc=2', '--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: 2026-02-11T16:30:09Z 2026-02-11 16:30:09.128218: E ./hilo/hlo_passes/NativeDfsHloVisitorWrapper.h:118] Source Info Unavailable [ERROR] [NCC_VRF010] Instruction check failed when handling %scatter.6923 = bf16[1,1,1024,256]{3,2,1,0} scatter(bf16[1,1,1024,256]{3,2,1,0} %p3, s64[1,1,1,256,4]{4,3,2,1,0} %concatenate.6919, f32[1,1,1,256]{3,2,1,0} %add.161), update_window_dims={}, inserted_window_dims={0,1,2,3}, scatter_dims_to_operand_dims={0,1,2,3}, index_vector_dim=4, to_apply=%ScatterCombiner.6920; see detailed errors below. TIP: Please rewrite using legal syntax of supported instructions, referring to `neuronx-cc list-operators --framework XLA`, or consider rewrite using NKI kernels, see https://awsdocs-neuron.readthedocs-hosted.com/en/latest/general/nki/index.html.
2
+ INTERNAL: Seen floating point types of different precisions in %scatter.6923 = bf16[1,1,1024,256]{3,2,1,0} scatter(%p3, %concatenate.6919, %add.161), update_window_dims={}, inserted_window_dims={0,1,2,3}, scatter_dims_to_operand_dims={0,1,2,3}, index_vector_dim=4, to_apply=%ScatterCombiner.6920, but mixed precision is disallowed.
3
+
neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4286ae3904bc1fc55b26e7da74a9b55089969e7beb0d7df4fea3fe327355be
3
+ size 2014792
neuronxcc-2.21.33363.0+82129205/MODULE_9f066b1410bb47e1dcbd+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba1a2542c7bfc637b844a55c6e2ea4318ee7bf2bb9ee2cd9980dd8b109e0a85
3
+ size 2161664
neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990114bdbe3f8cc7b952a958606722d0ce6986fd4c0ebeb4355dceb0f4d8f9ce
3
+ size 2654345
neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5e025f664251c58510567e48597963c1ef89defee69fa952be0a217ddf6061
3
+ size 2694144
neuronxcc-2.21.33363.0+82129205/MODULE_bfaed04f62fe477a5d8e+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a08d95dfe0d523891fc42c83d2a96cdb807d14e3d62973a4268afc37af8fdd9
3
+ size 2808969