Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF Staff commited on
Commit
e9a801a
·
verified ·
1 Parent(s): d08c6d9

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 +16 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/5eef7da50a217db5b302.json +97 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/qwen2/Qwen/Qwen2.5-0.5B/6f381e9a0d80f3d23d0b.json +97 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/452ec18c8952f9cf8540.json +149 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/765088ddf9ced28aa9a1.json +149 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/c1655182b84da2a4c42e.json +149 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/compile_flags.json +1 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.done +0 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.hlo_module.pb +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.neff +3 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/wrapped_neff.hlo +3 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/compile_flags.json +1 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.done +0 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.hlo_module.pb +3 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.neff +3 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/compile_flags.json +1 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.done +0 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.hlo_module.pb +3 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.neff +3 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/compile_flags.json +1 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.done +0 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.hlo_module.pb +3 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.neff +3 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/wrapped_neff.hlo +3 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/compile_flags.json +1 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.done +0 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.hlo_module.pb +3 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.neff +3 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/compile_flags.json +1 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.done +0 -0
  31. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.hlo_module.pb +3 -0
  32. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.neff +3 -0
  33. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/wrapped_neff.hlo +3 -0
  34. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/compile_flags.json +1 -0
  35. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.done +0 -0
  36. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.hlo_module.pb +3 -0
  37. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.neff +3 -0
  38. neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/compile_flags.json +1 -0
  39. neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.done +0 -0
  40. neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.hlo_module.pb +3 -0
  41. neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.neff +3 -0
  42. neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/wrapped_neff.hlo +3 -0
  43. neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/compile_flags.json +1 -0
  44. neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.done +0 -0
  45. neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.hlo_module.pb +3 -0
  46. neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.neff +3 -0
  47. neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/wrapped_neff.hlo +3 -0
  48. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+ed72d204/compile_flags.json +1 -0
  49. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+ed72d204/model.done +0 -0
  50. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+ed72d204/model.hlo_module.pb +3 -0
.gitattributes CHANGED
@@ -3992,3 +3992,19 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_90537ca32d559b5b82ed+a9d440f5/model.neff f
3992
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_90537ca32d559b5b82ed+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3993
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_b2f70bdbe8eeeceb6e97+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3994
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_b652d0e4d243f31a7a28+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3992
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_90537ca32d559b5b82ed+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3993
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_b2f70bdbe8eeeceb6e97+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3994
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_b652d0e4d243f31a7a28+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3995
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3996
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3997
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3998
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3999
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
4000
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4001
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4002
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
4003
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4004
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4005
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
4006
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4007
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
4008
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4009
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4010
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/5eef7da50a217db5b302.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "async_mode": false,
45
+ "attn_kernel_enabled": false,
46
+ "batch_size": 1,
47
+ "capacity_factor": null,
48
+ "cc_pipeline_tiling_factor": 2,
49
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
50
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
51
+ "continuous_batching": false,
52
+ "enable_bucketing": false,
53
+ "ep_degree": 1,
54
+ "flash_decoding_enabled": false,
55
+ "fused_qkv": false,
56
+ "glu_mlp": true,
57
+ "is_chunked_prefill": false,
58
+ "local_ranks_size": 2,
59
+ "logical_nc_config": 1,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 128,
62
+ "max_topk": 256,
63
+ "mlp_kernel_enabled": false,
64
+ "mlp_kernel_fuse_residual_add": false,
65
+ "n_active_tokens": 128,
66
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
67
+ "num_cores_per_group": 1,
68
+ "on_device_sampling": true,
69
+ "optimum_neuron_version": "0.3.1.dev0",
70
+ "output_logits": false,
71
+ "padding_side": "right",
72
+ "pp_degree": 1,
73
+ "qk_layernorm": false,
74
+ "qkv_kernel_enabled": false,
75
+ "rpl_reduce_dtype": "bfloat16",
76
+ "sequence_length": 128,
77
+ "sequence_parallel_enabled": false,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": null,
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2,
83
+ "vocab_parallel": false
84
+ },
85
+ "num_attention_heads": 14,
86
+ "num_hidden_layers": 24,
87
+ "num_key_value_heads": 2,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_scaling": null,
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": null,
92
+ "tie_word_embeddings": true,
93
+ "use_cache": true,
94
+ "use_mrope": false,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 151936
97
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/qwen2/Qwen/Qwen2.5-0.5B/6f381e9a0d80f3d23d0b.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "async_mode": false,
45
+ "attn_kernel_enabled": false,
46
+ "batch_size": 1,
47
+ "capacity_factor": null,
48
+ "cc_pipeline_tiling_factor": 2,
49
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
50
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
51
+ "continuous_batching": false,
52
+ "enable_bucketing": false,
53
+ "ep_degree": 1,
54
+ "flash_decoding_enabled": false,
55
+ "fused_qkv": false,
56
+ "glu_mlp": true,
57
+ "is_chunked_prefill": false,
58
+ "local_ranks_size": 2,
59
+ "logical_nc_config": 1,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 1024,
62
+ "max_topk": 256,
63
+ "mlp_kernel_enabled": false,
64
+ "mlp_kernel_fuse_residual_add": false,
65
+ "n_active_tokens": 1024,
66
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
67
+ "num_cores_per_group": 1,
68
+ "on_device_sampling": true,
69
+ "optimum_neuron_version": "0.3.1.dev1",
70
+ "output_logits": false,
71
+ "padding_side": "right",
72
+ "pp_degree": 1,
73
+ "qk_layernorm": false,
74
+ "qkv_kernel_enabled": false,
75
+ "rpl_reduce_dtype": "bfloat16",
76
+ "sequence_length": 1024,
77
+ "sequence_parallel_enabled": false,
78
+ "speculation_length": 0,
79
+ "start_rank_id": 0,
80
+ "target": null,
81
+ "torch_dtype": "bfloat16",
82
+ "tp_degree": 2,
83
+ "vocab_parallel": false
84
+ },
85
+ "num_attention_heads": 14,
86
+ "num_hidden_layers": 24,
87
+ "num_key_value_heads": 2,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_scaling": null,
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": null,
92
+ "tie_word_embeddings": true,
93
+ "use_cache": true,
94
+ "use_mrope": false,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 151936
97
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/452ec18c8952f9cf8540.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "HuggingFaceTB/SmolLM3-3B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "SmolLM3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
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
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "neuron": {
57
+ "_serialized_key": "NxDNeuronConfig",
58
+ "async_mode": false,
59
+ "attn_kernel_enabled": false,
60
+ "batch_size": 1,
61
+ "capacity_factor": null,
62
+ "cc_pipeline_tiling_factor": 2,
63
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
64
+ "checkpoint_revision": "988f1dde6bd2a36e3e7f45777a36507ea004fe22",
65
+ "continuous_batching": false,
66
+ "enable_bucketing": false,
67
+ "ep_degree": 1,
68
+ "flash_decoding_enabled": false,
69
+ "fused_qkv": true,
70
+ "glu_mlp": true,
71
+ "is_chunked_prefill": false,
72
+ "local_ranks_size": 2,
73
+ "logical_nc_config": 1,
74
+ "max_batch_size": 1,
75
+ "max_context_length": 4096,
76
+ "max_topk": 256,
77
+ "mlp_kernel_enabled": false,
78
+ "mlp_kernel_fuse_residual_add": false,
79
+ "n_active_tokens": 4096,
80
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
81
+ "num_cores_per_group": 1,
82
+ "on_device_sampling": true,
83
+ "optimum_neuron_version": "0.3.1.dev1",
84
+ "output_logits": false,
85
+ "padding_side": "right",
86
+ "pp_degree": 1,
87
+ "qk_layernorm": false,
88
+ "qkv_kernel_enabled": false,
89
+ "rpl_reduce_dtype": "bfloat16",
90
+ "sequence_length": 4096,
91
+ "sequence_parallel_enabled": false,
92
+ "speculation_length": 0,
93
+ "start_rank_id": 0,
94
+ "target": null,
95
+ "torch_dtype": "bfloat16",
96
+ "tp_degree": 2,
97
+ "vocab_parallel": false
98
+ },
99
+ "no_rope_layer_interval": 4,
100
+ "no_rope_layers": [
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 0,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 0,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 0,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 0,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 0,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 0,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 0,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 0,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 0
137
+ ],
138
+ "num_attention_heads": 16,
139
+ "num_hidden_layers": 36,
140
+ "num_key_value_heads": 4,
141
+ "pretraining_tp": 2,
142
+ "rms_norm_eps": 1e-06,
143
+ "rope_scaling": null,
144
+ "rope_theta": 5000000.0,
145
+ "sliding_window": null,
146
+ "use_cache": false,
147
+ "use_sliding_window": false,
148
+ "vocab_size": 128256
149
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/765088ddf9ced28aa9a1.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "HuggingFaceTB/SmolLM3-3B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "SmolLM3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
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
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "neuron": {
57
+ "_serialized_key": "NxDNeuronConfig",
58
+ "async_mode": false,
59
+ "attn_kernel_enabled": false,
60
+ "batch_size": 16,
61
+ "capacity_factor": null,
62
+ "cc_pipeline_tiling_factor": 2,
63
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
64
+ "checkpoint_revision": "988f1dde6bd2a36e3e7f45777a36507ea004fe22",
65
+ "continuous_batching": true,
66
+ "enable_bucketing": false,
67
+ "ep_degree": 1,
68
+ "flash_decoding_enabled": false,
69
+ "fused_qkv": true,
70
+ "glu_mlp": true,
71
+ "is_chunked_prefill": false,
72
+ "local_ranks_size": 2,
73
+ "logical_nc_config": 1,
74
+ "max_batch_size": 16,
75
+ "max_context_length": 4096,
76
+ "max_topk": 256,
77
+ "mlp_kernel_enabled": false,
78
+ "mlp_kernel_fuse_residual_add": false,
79
+ "n_active_tokens": 4096,
80
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
81
+ "num_cores_per_group": 1,
82
+ "on_device_sampling": true,
83
+ "optimum_neuron_version": "0.3.1.dev1",
84
+ "output_logits": false,
85
+ "padding_side": "right",
86
+ "pp_degree": 1,
87
+ "qk_layernorm": false,
88
+ "qkv_kernel_enabled": false,
89
+ "rpl_reduce_dtype": "bfloat16",
90
+ "sequence_length": 4096,
91
+ "sequence_parallel_enabled": false,
92
+ "speculation_length": 0,
93
+ "start_rank_id": 0,
94
+ "target": null,
95
+ "torch_dtype": "bfloat16",
96
+ "tp_degree": 2,
97
+ "vocab_parallel": false
98
+ },
99
+ "no_rope_layer_interval": 4,
100
+ "no_rope_layers": [
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 0,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 0,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 0,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 0,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 0,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 0,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 0,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 0,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 0
137
+ ],
138
+ "num_attention_heads": 16,
139
+ "num_hidden_layers": 36,
140
+ "num_key_value_heads": 4,
141
+ "pretraining_tp": 2,
142
+ "rms_norm_eps": 1e-06,
143
+ "rope_scaling": null,
144
+ "rope_theta": 5000000.0,
145
+ "sliding_window": null,
146
+ "use_cache": false,
147
+ "use_sliding_window": false,
148
+ "vocab_size": 128256
149
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/c1655182b84da2a4c42e.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "HuggingFaceTB/SmolLM3-3B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "SmolLM3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
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
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "max_window_layers": 28,
54
+ "mlp_bias": false,
55
+ "model_type": "smollm3",
56
+ "neuron": {
57
+ "_serialized_key": "NxDNeuronConfig",
58
+ "async_mode": false,
59
+ "attn_kernel_enabled": false,
60
+ "batch_size": 4,
61
+ "capacity_factor": null,
62
+ "cc_pipeline_tiling_factor": 2,
63
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
64
+ "checkpoint_revision": "988f1dde6bd2a36e3e7f45777a36507ea004fe22",
65
+ "continuous_batching": true,
66
+ "enable_bucketing": false,
67
+ "ep_degree": 1,
68
+ "flash_decoding_enabled": false,
69
+ "fused_qkv": true,
70
+ "glu_mlp": true,
71
+ "is_chunked_prefill": false,
72
+ "local_ranks_size": 2,
73
+ "logical_nc_config": 1,
74
+ "max_batch_size": 4,
75
+ "max_context_length": 16384,
76
+ "max_topk": 256,
77
+ "mlp_kernel_enabled": false,
78
+ "mlp_kernel_fuse_residual_add": false,
79
+ "n_active_tokens": 16384,
80
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
81
+ "num_cores_per_group": 1,
82
+ "on_device_sampling": true,
83
+ "optimum_neuron_version": "0.3.1.dev1",
84
+ "output_logits": false,
85
+ "padding_side": "right",
86
+ "pp_degree": 1,
87
+ "qk_layernorm": false,
88
+ "qkv_kernel_enabled": false,
89
+ "rpl_reduce_dtype": "bfloat16",
90
+ "sequence_length": 16384,
91
+ "sequence_parallel_enabled": false,
92
+ "speculation_length": 0,
93
+ "start_rank_id": 0,
94
+ "target": null,
95
+ "torch_dtype": "bfloat16",
96
+ "tp_degree": 2,
97
+ "vocab_parallel": false
98
+ },
99
+ "no_rope_layer_interval": 4,
100
+ "no_rope_layers": [
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 0,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 0,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 0,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 0,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 0,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 0,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 0,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 0,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 0
137
+ ],
138
+ "num_attention_heads": 16,
139
+ "num_hidden_layers": 36,
140
+ "num_key_value_heads": 4,
141
+ "pretraining_tp": 2,
142
+ "rms_norm_eps": 1e-06,
143
+ "rope_scaling": null,
144
+ "rope_theta": 5000000.0,
145
+ "sliding_window": null,
146
+ "use_cache": false,
147
+ "use_sliding_window": false,
148
+ "vocab_size": 128256
149
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+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_198b5b02b387709019ea+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8f5d32b8321f6989bc9d43d673308f019fb067e57bbd2f5c8527a85e87e4b6
3
+ size 620149
neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facf98bc7d48c576ca0fdc114ae50d716ac5f4073dbbbab77f15058e1172aa51
3
+ size 1106944
neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b103a337ecc4130bd48980789b5e20d873a619e12a86fc5e8663891fa97253f
3
+ size 1251970
neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+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_389bcc74371d275ea994+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84620525e12229c74c885c0ce3e0225158e4074a231ef29a6cb1427dd5834639
3
+ size 155181
neuronxcc-2.19.8089.0+8ab9f450/MODULE_389bcc74371d275ea994+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717c56ebc06cff5d0cdd82a0ce1268c626baafdb8cb2f7f4f569257db24d5d6d
3
+ size 3267584
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+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_5d8b3bbf6ba518b8162f+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71939c494e52b35bec2295aff99bd7f69bc8ef24a7f82332fe817463fd82d580
3
+ size 1036280
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f538962d0b2643238cbf7c34852046be3bba640e7007ac75555267e10dea7471
3
+ size 10681344
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+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_7076b883d5c8650d94da+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061f2ed785d97393ab0d7a173f5cff55108edd720bea0016ab95ff8dc27b964e
3
+ size 864561
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c851212dbcfd36482be8f6b99e912b32619c33a416cf3dabfacc2dae36d76eb
3
+ size 8233984
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba3391169072ac8478f0519b0c2a159af020c222f1a93fe3bb8bd64216281bd
3
+ size 8391033
neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+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_837bdb7b4c4f834e67af+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476aad74c9f0f0a753fcfd10d1a52ba8fc70d203b6656393faf43779213abbe3
3
+ size 1044964
neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313bb2fac82d154054c4188f06dec6675923e7b3e99c6e330a0a6f03d5e678e8
3
+ size 75060224
neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+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_83e84045fc71578eb073+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f535bf4362204976aae951872527015d027b44f19301788efbc4790f69df145d
3
+ size 621840
neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c99c1c48449542c4e92bea86fa319e46171a5b9f2e93e5c581f7be6689ce4a
3
+ size 1895424
neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99dc771226f91f120ddb25b037f66df0b59a9d1506cb017150067588e75dae3
3
+ size 2040790
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+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_a9ae7a29deecc8ce3b7e+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d202063a9984d602feaaf2c700afcc07ee5b1a307c2095762c14881240f14b
3
+ size 710874
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88110d333f8f10177d95d2263884a0a33e2743edbe25cfce395001990eb2db2c
3
+ size 54508544
neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+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_aa860ba18e95034cf093+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee545e981e023f9ea361f2f60a26fa52fa682607225bf3b6eb0ea11fb36a86f
3
+ size 862478
neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f46da234144703e575f63dbcc2d7c49b49b21c1a380b1677f907f501f3fd4f
3
+ size 6913024
neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876ed0fa40920c6776e14c4b6ef4b23753c635e562d81003a9284c26a28b7ef1
3
+ size 7069565
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+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_af00345a8f045c9c3128+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a27ffe177d303d6fff091b8112fd026019009013b54d75aa67c97b2ec4c5c83
3
+ size 861528
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04daa061d8443bc13eca4a4a385fde4b599cbcc33b699296fd704d0173df0491
3
+ size 4015104
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af00345a8f045c9c3128+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2039c6e7168c45a13b847f5ad181344cb2ee870be409a40bf4db922bbdb9cf62
3
+ size 4171645
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+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_c95f9cae22467b36d97b+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c95f9cae22467b36d97b+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6beff2011fa69bed4b6788c3e787d5099c70fa4cddc7b20d16c92507361a3d
3
+ size 957736