Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
71993be
·
verified ·
1 Parent(s): 9b0c04c

Synchronizing local compiler cache.

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +19 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-0.6B/11315149f2fec5f9b1e3.json +87 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/040b1e23663eba2981b3.json +87 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/6f5f2cf26c21b525ca82.json +87 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/8f2f6fc022fb92a08835.json +87 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/922b8f110b9e3fdaa766.json +87 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-8B/3c013915c647bb8e6712.json +95 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-8B/b60a4e37d9a2dbabe961.json +95 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/compile_flags.json +1 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.done +0 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.hlo_module.pb +3 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.neff +3 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e5b82b136a38372d842+6e4949b4/model.hlo_module.pb +1 -1
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e5b82b136a38372d842+6e4949b4/model.neff +1 -1
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff +1 -1
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo +1 -1
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/compile_flags.json +1 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/model.hlo_module.pb +3 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/model.log +3 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/compile_flags.json +1 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.done +0 -0
  22. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.hlo_module.pb +3 -0
  23. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.neff +3 -0
  24. neuronxcc-2.21.18209.0+043b1bf7/MODULE_34362baee2ad4784108e+a02c3a36/model.neff +1 -1
  25. neuronxcc-2.21.18209.0+043b1bf7/MODULE_34362baee2ad4784108e+a02c3a36/wrapped_neff.hlo +1 -1
  26. neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/compile_flags.json +1 -0
  27. neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.done +0 -0
  28. neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.hlo_module.pb +3 -0
  29. neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.neff +3 -0
  30. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3e3c9e9db5ebafa6c488+a02c3a36/model.neff +1 -1
  31. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3e3c9e9db5ebafa6c488+a02c3a36/wrapped_neff.hlo +1 -1
  32. neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/compile_flags.json +1 -0
  33. neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.done +0 -0
  34. neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.hlo_module.pb +3 -0
  35. neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.neff +3 -0
  36. neuronxcc-2.21.18209.0+043b1bf7/MODULE_574e9a764503b48fbba9+24129607/model.hlo_module.pb +1 -1
  37. neuronxcc-2.21.18209.0+043b1bf7/MODULE_574e9a764503b48fbba9+24129607/model.neff +1 -1
  38. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/compile_flags.json +1 -0
  39. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.done +0 -0
  40. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.hlo_module.pb +3 -0
  41. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.neff +3 -0
  42. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b1c456704a89716d745+2dde74c7/model.neff +1 -1
  43. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b1c456704a89716d745+2dde74c7/wrapped_neff.hlo +1 -1
  44. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5f6f4f62aba29e11d946+24129607/model.hlo_module.pb +1 -1
  45. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5f6f4f62aba29e11d946+24129607/model.neff +1 -1
  46. neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/compile_flags.json +1 -0
  47. neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.done +0 -0
  48. neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.hlo_module.pb +3 -0
  49. neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.neff +3 -0
  50. neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b37881de0fe95bd8128+24129607/compile_flags.json +1 -0
.gitattributes CHANGED
@@ -5466,3 +5466,22 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_b3156313afcf6f9c1c2b+24129607/model.neff
5466
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_ea6d0b2d03e12e6e6709+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5467
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_f668e8059b4ad00c098b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5468
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_f668e8059b4ad00c098b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5466
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_ea6d0b2d03e12e6e6709+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5467
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_f668e8059b4ad00c098b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5468
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_f668e8059b4ad00c098b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5469
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5470
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5471
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5472
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5473
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5474
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5475
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b37881de0fe95bd8128+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5476
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_823cb759235f53a8fe88+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5477
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a0387fe4d05bf37e345a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
5478
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a0387fe4d05bf37e345a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5479
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_af5ca2287a6b0d70aac7+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5480
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_bd3408e2c963ac7da056+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5481
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_c345ba838e8c529a43e2+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5482
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_cb4d848c61c58d4a5351+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5483
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_ce7eb4c5ef357b61cc09+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5484
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_da126386d4d4d4a5bf4f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5485
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_dd4aa1e96fd3b31b162d+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
5486
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_de1482f217f05f48d1dd+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
5487
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4bed0e6c1426c4b9bc7+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-0.6B/11315149f2fec5f9b1e3.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 40960,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
54
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 2,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 4096,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 4096,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": true,
66
+ "optimum_neuron_version": "0.4.2.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 4096,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn1",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 2
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151936
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/040b1e23663eba2981b3.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 6,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
54
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 24,
60
+ "max_batch_size": 6,
61
+ "max_context_length": 1024,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 1024,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.2.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 1024,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn1",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 24
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151669
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/6f5f2cf26c21b525ca82.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
54
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 1,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 4096,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 4096,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.2.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 4096,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn1",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 1
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151669
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/8f2f6fc022fb92a08835.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 4,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
54
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 24,
60
+ "max_batch_size": 4,
61
+ "max_context_length": 1024,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 1024,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.2.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 1024,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn1",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 24
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151669
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/922b8f110b9e3fdaa766.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
54
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 24,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 1024,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 1024,
64
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.2.dev0",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 1024,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn1",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 24
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151669
87
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-8B/3c013915c647bb8e6712.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-8B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 12288,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 40960,
55
+ "max_window_layers": 36,
56
+ "model_type": "qwen3",
57
+ "neuron": {
58
+ "_serialized_key": "NxDNeuronConfig",
59
+ "batch_size": 1,
60
+ "capacity_factor": null,
61
+ "checkpoint_id": "Qwen/Qwen3-Embedding-8B",
62
+ "checkpoint_revision": "1d8ad4ca9b3dd8059ad90a75d4983776a23d44af",
63
+ "continuous_batching": false,
64
+ "ep_degree": 1,
65
+ "fused_qkv": true,
66
+ "glu_mlp": true,
67
+ "local_ranks_size": 2,
68
+ "max_batch_size": 1,
69
+ "max_context_length": 4096,
70
+ "max_topk": 256,
71
+ "n_active_tokens": 4096,
72
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
73
+ "on_device_sampling": false,
74
+ "optimum_neuron_version": "0.4.2.dev0",
75
+ "output_logits": false,
76
+ "pp_degree": 1,
77
+ "sequence_length": 4096,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": "trn1",
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2
83
+ },
84
+ "num_attention_heads": 32,
85
+ "num_hidden_layers": 36,
86
+ "num_key_value_heads": 8,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_scaling": null,
89
+ "rope_theta": 1000000,
90
+ "sliding_window": null,
91
+ "tie_word_embeddings": false,
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "vocab_size": 151665
95
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.2.dev0/qwen3/Qwen/Qwen3-Embedding-8B/b60a4e37d9a2dbabe961.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-8B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 12288,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 40960,
55
+ "max_window_layers": 36,
56
+ "model_type": "qwen3",
57
+ "neuron": {
58
+ "_serialized_key": "NxDNeuronConfig",
59
+ "batch_size": 16,
60
+ "capacity_factor": null,
61
+ "checkpoint_id": "Qwen/Qwen3-Embedding-8B",
62
+ "checkpoint_revision": "1d8ad4ca9b3dd8059ad90a75d4983776a23d44af",
63
+ "continuous_batching": false,
64
+ "ep_degree": 1,
65
+ "fused_qkv": true,
66
+ "glu_mlp": true,
67
+ "local_ranks_size": 2,
68
+ "max_batch_size": 16,
69
+ "max_context_length": 4096,
70
+ "max_topk": 256,
71
+ "n_active_tokens": 4096,
72
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
73
+ "on_device_sampling": false,
74
+ "optimum_neuron_version": "0.4.2.dev0",
75
+ "output_logits": false,
76
+ "pp_degree": 1,
77
+ "sequence_length": 4096,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": "trn1",
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2
83
+ },
84
+ "num_attention_heads": 32,
85
+ "num_hidden_layers": 36,
86
+ "num_key_value_heads": 8,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_scaling": null,
89
+ "rope_theta": 1000000,
90
+ "sliding_window": null,
91
+ "tie_word_embeddings": false,
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "vocab_size": 151665
95
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7607df5f2c7c5132d87730619aa3366ddb2035e223a239aa5a14a1c9d7469d57
3
+ size 848773
neuronxcc-2.21.18209.0+043b1bf7/MODULE_06cc3d220bd81f31483c+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d799faaff5e25a7531d12f187cea88faf79b29e045c2b88d2c3ea0b8bd94cab
3
+ size 5786624
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e5b82b136a38372d842+6e4949b4/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00ef644e5979852b4384b292b9654db3d05671a18e7c2997041f8228841c496b
3
  size 84807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb0a23b716925f843a16e15f9f0385f067950c8f9f55cd7b3db583ba03b1a7e
3
  size 84807
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e5b82b136a38372d842+6e4949b4/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8c78397b4802378ef5aed6265b491f7d9f2c88d33d42c672b8394aa40fbad78
3
  size 646144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f26bc2e40e6e21bffa40348dd28785a0c5ba6ae26126553c85435559849af5d
3
  size 646144
neuronxcc-2.21.18209.0+043b1bf7/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be0a2ca1ec6303e7c7f1f96a0c58635b22fcc2c5566988781cf2876a2f11f9d6
3
  size 277504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690971e38e78e6e8e2e0b2249904244dbe845f18a1d36cb2b763deac5fe550f3
3
  size 277504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1941f77c35018b572d2296e153bda0c1a82b578f3486e690f2e095e5936a2009
3
  size 285854
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937aba417c7465954a0bf71e8d536e6ce2db41d44b477deb724f8f6154f76e19
3
  size 285854
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949343b64aaeb75ac893058b4181a58759ab30c14ab879041244bb9af4356695
3
+ size 850786
neuronxcc-2.21.18209.0+043b1bf7/MODULE_315d9491c827c077575a+fb4cc044/model.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/encoding/_tp0_bk0/model.MODULE_315d9491c827c077575a+fb4cc044.hlo_module.pb', '--output', '/tmp/nxd_model/encoding/_tp0_bk0/model.MODULE_315d9491c827c077575a+fb4cc044.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/encoding/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815] Estimated peak HBM usage (19.257GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - 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
+ 2025-11-07T14:10:10Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815] Estimated peak HBM usage (19.257GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - 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-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e6c39ae5aaa2365e0018b111269da40c42b131faed18711a8810bedd68a436
3
+ size 429397
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3321b4e97123c041192d+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0135e8fa145738be49848914c2dbb2c52c3854a2403644f1842244e432ed0fe
3
+ size 1352704
neuronxcc-2.21.18209.0+043b1bf7/MODULE_34362baee2ad4784108e+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d03c6300c55f1b499d9c5d804143ff8484a494001339977d2f2296b1ce816fce
3
  size 246784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc574992e72adfe26c916de4e344ec745c5f0367620c1183437c3127f9fef15
3
  size 246784
neuronxcc-2.21.18209.0+043b1bf7/MODULE_34362baee2ad4784108e+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bdbe143e93e40a8157c3303918d7b4ab8d3c4603949e1cf14e9bcf86f43e8aa
3
  size 255104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3995a13290761f8f6f89854871f6a5da48002e637efad7b67cec72e826cc1e
3
  size 255104
neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a36ee034700342382b6da2932f74a5d63b34f8b66d47da8dcd5b0cf42842dd7
3
+ size 428915
neuronxcc-2.21.18209.0+043b1bf7/MODULE_394461f5b793e1c6ddbd+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2978f644a5df5278f76096838837e039d1d5a3dc2cf4e9c2a6cae1784f9bec0
3
+ size 4199424
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3e3c9e9db5ebafa6c488+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3d4458ffd347738badcf0b23d0d413a4d36cf853e122a45c2206886aebff211
3
  size 216064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40684a5208697e733fd92b531e426c9a49e2e2f3dce8fdc81afe434818f265f2
3
  size 216064
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3e3c9e9db5ebafa6c488+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fe259afa434f354cd2ea4cbfa55677adfcd4de255474e7d13f3ee086220a609
3
  size 224412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e490cb2df34ae3582e58811ed1a9ea678ca780e9525b51113490839860539904
3
  size 224412
neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f01851ab7ef0b0809a16c7e907029400056497364b603f59ab2c9f38e6cfc9d
3
+ size 427538
neuronxcc-2.21.18209.0+043b1bf7/MODULE_45c1a0c25eab451751df+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d530cd99cdeac86375ed3d4ee421b5db73c2cc8ec537732e3f811d227f4c1e
3
+ size 4158464
neuronxcc-2.21.18209.0+043b1bf7/MODULE_574e9a764503b48fbba9+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b830e756a066effbee9464b2f0ee872654f088ddd85afe47df42d75321a6961b
3
  size 1061093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c27fc5e9a14dd0d728587d4b5e633e65e6902974129e23c485ea65109a7a63
3
  size 1061093
neuronxcc-2.21.18209.0+043b1bf7/MODULE_574e9a764503b48fbba9+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f3d938502148f35e5dcbd5ffabf9a05f9faf681ad9f9e99b65cf52a927b8cce
3
  size 9473024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ca12a9af7e210d81d5d48764b74bea3ad2c8dee1d5f6ec04b511070e5aa4ca
3
  size 9473024
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6b6bf0feffa5e590b798a1c60710db88bec1cb49364a0829ce08a05370a91d
3
+ size 435194
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5988b4b9e2fe27c7105c+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f32b334d4b29c0442354fbb4970d0103862810dbab9dd6e1d90f2943d2fad5
3
+ size 4731904
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b1c456704a89716d745+2dde74c7/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4108281a03ea281002e10678a110e666893df5d987032383a0e7ad4e096dbeaa
3
  size 369664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d1a66ec4620a7bbd95ddcd3f0b8563e7b9fd48c9167bbb83e09de5ea8f2045
3
  size 369664
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b1c456704a89716d745+2dde74c7/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90c34fd1fb81a015236d8dc844fa950ab15b39579c066d78a8bec47f68c41d2c
3
  size 379362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d780e7908fb2043598326a014149c1adc7cf79ede14eaac7e57a0efd5aaaf1f
3
  size 379362
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5f6f4f62aba29e11d946+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fe38c017b84f73b7d3ea59c6211db2ed9d5c219e724f7fa46268df0122085b
3
  size 694128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b57a81178b87e2fa8d72c53f158790060e6f323a7ea625353c0c2ecec75b33d
3
  size 694128
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5f6f4f62aba29e11d946+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1e4c997fc85f924fab368f5e7c1be4735d973e2370b8619493ad63aa1e5acbf
3
  size 625664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94b84c6a5ac7142334a119a16754827bff07c49ce7dd2d1b9f71d6c2d29a755
3
  size 625664
neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec5e1a252b77227b0d8bf55d0ad8984aaaf05d34c12fbff567fc48bf7f1f98e
3
+ size 431779
neuronxcc-2.21.18209.0+043b1bf7/MODULE_616029436a1201c3f014+fb4cc044/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15884b84559dd7029720a5a83714e250e569eee383b805015a1b0a990e58ebc
3
+ size 4158464
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b37881de0fe95bd8128+24129607/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/_tp0_bk0/log-neuron-cc.txt"]