Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
5cca1cb
·
verified ·
1 Parent(s): a30864f

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 +17 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json +102 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/66509396a74c016d41b0.json +62 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0df19da9c3c531250d2.json +62 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/9a3f48228cf1a10a6db2.json +87 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.json +87 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb +1 -1
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff +1 -1
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff +1 -1
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo +1 -1
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb +1 -1
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff +1 -1
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb +1 -1
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff +1 -1
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb +1 -1
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff +1 -1
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/compile_flags.json +1 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.done +0 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.hlo_module.pb +3 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff +3 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/compile_flags.json +1 -0
  22. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.done +0 -0
  23. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.hlo_module.pb +3 -0
  24. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff +3 -0
  25. neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo +3 -0
  26. neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/compile_flags.json +1 -0
  27. neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.done +0 -0
  28. neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.hlo_module.pb +3 -0
  29. neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff +3 -0
  30. neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo +3 -0
  31. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/compile_flags.json +1 -0
  32. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.done +0 -0
  33. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.hlo_module.pb +3 -0
  34. neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff +3 -0
  35. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff +1 -1
  36. neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo +1 -1
  37. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff +1 -1
  38. neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo +1 -1
  39. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff +1 -1
  40. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo +1 -1
  41. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/compile_flags.json +1 -0
  42. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.done +0 -0
  43. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.hlo_module.pb +3 -0
  44. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff +3 -0
  45. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff +1 -1
  46. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo +1 -1
  47. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb +1 -1
  48. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff +1 -1
  49. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/compile_flags.json +1 -0
  50. neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.done +0 -0
.gitattributes CHANGED
@@ -5325,3 +5325,20 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff
5325
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5326
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5327
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5325
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5326
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5327
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5328
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5329
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5330
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5331
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5332
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5333
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5334
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
5335
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
5336
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5337
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
5338
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron filter=lfs diff=lfs merge=lfs -text
5339
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
5340
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
5341
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.neff filter=lfs diff=lfs merge=lfs -text
5342
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5343
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.neff filter=lfs diff=lfs merge=lfs -text
5344
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "MultiModelCacheEntry",
3
+ "_model_id": "PixArt-alpha/PixArt-XL-2-512x512",
4
+ "_task": null,
5
+ "text_encoder": {
6
+ "architectures": [
7
+ "T5EncoderModel"
8
+ ],
9
+ "classifier_dropout": 0.0,
10
+ "d_ff": 10240,
11
+ "d_kv": 64,
12
+ "d_model": 4096,
13
+ "decoder_start_token_id": 0,
14
+ "dense_act_fn": "gelu_new",
15
+ "dropout_rate": 0.1,
16
+ "export_model_type": "t5-encoder",
17
+ "feed_forward_proj": "gated-gelu",
18
+ "initializer_factor": 1.0,
19
+ "is_encoder_decoder": false,
20
+ "is_gated_act": true,
21
+ "layer_norm_epsilon": 1e-06,
22
+ "model_type": "t5",
23
+ "neuron": {
24
+ "auto_cast": null,
25
+ "auto_cast_type": null,
26
+ "compiler_type": "neuronx-cc",
27
+ "compiler_version": "2.21.18209.0+043b1bf7",
28
+ "dynamic_batch_size": false,
29
+ "float_dtype": "fp32",
30
+ "inline_weights_to_neff": false,
31
+ "instance_type": "trn1",
32
+ "int_dtype": "int64",
33
+ "optlevel": "2",
34
+ "output_attentions": false,
35
+ "output_hidden_states": false,
36
+ "static_batch_size": 1,
37
+ "static_sequence_length": 120,
38
+ "task": "feature-extraction",
39
+ "tensor_parallel_size": 1
40
+ },
41
+ "num_decoder_layers": 24,
42
+ "num_heads": 64,
43
+ "num_layers": 24,
44
+ "output_past": true,
45
+ "relative_attention_max_distance": 128,
46
+ "relative_attention_num_buckets": 32,
47
+ "tie_word_embeddings": false,
48
+ "use_cache": false,
49
+ "vocab_size": 32128
50
+ },
51
+ "transformer": {
52
+ "_class_name": "PixArtTransformer2DModel",
53
+ "activation_fn": "gelu-approximate",
54
+ "attention_bias": true,
55
+ "attention_head_dim": 72,
56
+ "attention_type": "default",
57
+ "caption_channels": 4096,
58
+ "cross_attention_dim": 1152,
59
+ "double_self_attention": false,
60
+ "dropout": 0.0,
61
+ "in_channels": 4,
62
+ "interpolation_scale": null,
63
+ "neuron": {
64
+ "auto_cast": null,
65
+ "auto_cast_type": null,
66
+ "compiler_type": "neuronx-cc",
67
+ "compiler_version": "2.21.18209.0+043b1bf7",
68
+ "dynamic_batch_size": false,
69
+ "float_dtype": "bf16",
70
+ "inline_weights_to_neff": false,
71
+ "instance_type": "trn1",
72
+ "int_dtype": "int64",
73
+ "optlevel": "2",
74
+ "output_attentions": false,
75
+ "output_hidden_states": false,
76
+ "static_batch_size": 1,
77
+ "static_encoder_hidden_size": 4096,
78
+ "static_height": 64,
79
+ "static_num_channels": 4,
80
+ "static_sequence_length": 120,
81
+ "static_vae_scale_factor": 8,
82
+ "static_width": 64,
83
+ "task": "semantic-segmentation",
84
+ "tensor_parallel_size": 1
85
+ },
86
+ "norm_elementwise_affine": false,
87
+ "norm_eps": 1e-06,
88
+ "norm_num_groups": 32,
89
+ "norm_type": "ada_norm_single",
90
+ "num_attention_heads": 16,
91
+ "num_embeds_ada_norm": 1000,
92
+ "num_layers": 28,
93
+ "num_vector_embeds": null,
94
+ "only_cross_attention": false,
95
+ "out_channels": 8,
96
+ "output_attentions": false,
97
+ "patch_size": 2,
98
+ "upcast_attention": false,
99
+ "use_additional_conditions": null,
100
+ "use_linear_projection": false
101
+ }
102
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/66509396a74c016d41b0.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "llamafactory/tiny-random-Llama-3",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 4,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 16,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 64,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "batch_size": 2,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
23
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
24
+ "continuous_batching": true,
25
+ "enable_bucketing": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 2,
31
+ "max_context_length": 128,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 128,
34
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.1.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 128,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "float16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 2,
48
+ "num_key_value_heads": 4,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "use_cache": true,
61
+ "vocab_size": 128256
62
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0df19da9c3c531250d2.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "llamafactory/tiny-random-Llama-3",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 4,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 16,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 64,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "batch_size": 2,
21
+ "capacity_factor": null,
22
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
23
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
24
+ "continuous_batching": true,
25
+ "enable_bucketing": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 2,
31
+ "max_context_length": 128,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 128,
34
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.1.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 128,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "float16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 2,
48
+ "num_key_value_heads": 4,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "use_cache": true,
61
+ "vocab_size": 128256
62
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/9a3f48228cf1a10a6db2.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
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
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
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "neuron": {
49
+ "_serialized_key": "NxDNeuronConfig",
50
+ "batch_size": 1,
51
+ "capacity_factor": null,
52
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
53
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
54
+ "continuous_batching": false,
55
+ "enable_bucketing": 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": "0.4.1.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/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.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
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
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
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "neuron": {
49
+ "_serialized_key": "NxDNeuronConfig",
50
+ "batch_size": 1,
51
+ "capacity_factor": null,
52
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
53
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
54
+ "continuous_batching": false,
55
+ "enable_bucketing": 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": 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": "0.4.1.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": 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/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:017fd1b59af56e134a8f3ae77b50bce4960bf820c2291967f002dc627a69a99f
3
  size 84807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61586b49e1e903cab9fff0482909f040c5e97621b59f6233899973b7cd27184d
3
  size 84807
neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6197fd677022e4562f06c9013a1ea531d8c0b4822263cec87758f73893cbc883
3
  size 646144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33b221d4039eaaa99cb40b84d626d05299fe802098783ac5418f3b32574abe8
3
  size 646144
neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:995dde6558ec218034ee6bfadb9001d15666f60d47e1bfb96959c4374f4a5160
3
  size 246784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d9f3177230710833e1a22c473ceb0215149d4996fb169ded5f87e0ebd9b6e7
3
  size 246784
neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c965d92c0838f2172d1ce99ae28e8b19fe85df43e821f94e31751dec2b5e4af3
3
  size 255104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11296a74882475c7e044dddae990ac1e06a377d292f8bbbabccbf9f52a68de87
3
  size 255104
neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2aaa679a020415ee5b0946c6980026f3673ecebec68d8bd20e9a1e942b71265
3
  size 81516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010699d8fe7fd543b752b93c8bc2cd72e5309050ab149427dfd589c97e7268c5
3
  size 81516
neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9939f9bf1f6e046ae9968d2ddd8afa415064ae1d7bb0acbba84ef85296090aa3
3
  size 267264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bf12c475e30b9ae5c3e55dc492a5b36e2b84326264d9707f19e411d4862c1a
3
  size 267264
neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b9548012c66a27d1734252c9d5e13bebf8352e9b795d8395badbb16c34b4bb0
3
  size 97794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c4af19c1f6118b30a135c4553925fc304a74428ae95971dcad784cdef2729b
3
  size 97794
neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8f073ed10513531bcaf542a905eb5d80704a541a1ea5cfc869af061504a489a
3
  size 410624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3706159398be1c857cb9410baa841093252d4bd2db4a6ec6e5fcfcb5866e59d
3
  size 410624
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41cc515d48e8260f02395a97fb96cf882b6bbd63dd1e0459ca611c93200db368
3
  size 90382
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d1111cccd29ce4edd640c6b5880fa7b920b5c1211396da06d3b58670ec7a12
3
  size 90382
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c11a3ad3c54f42fd4888286b0d1a3dc80638dfc20a5001b3d0166c89a0f84e5b
3
  size 359424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07848927e2ef873e5477430034ef70cac7c7af77f9e216a81255e421762ed85
3
  size 359424
neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/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_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a176554451485ee2e3396bd66f6314c482af73ae61ff4b5a2b90786765a642
3
+ size 1289358
neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f091182eeac4dcf274fb36008a9da3f4ae0df8e42294735025761bc95389713c
3
+ size 728064
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+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-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d27d563a4e3028e4ea49838d9c3b5f1557c20ff9dd0f09d8fc5f9c669102fbe
3
+ size 658192
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6bd5080e30cb75bdd6b2157daeb16e6c52ad35e65ccdaa0a523408517ec0ea
3
+ size 1915904
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a5ae8a75a3a4e0656c3937dc2bec0710df3820ba3db609ff551cf806a50c75
3
+ size 2053551
neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d477f34ae752f5a59c170824b8b4808870f92b137ec5c4cf7cb18299e7a0c7
3
+ size 1574268
neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b439829eb058574688a6b0736453d69ba3ab5c982d01d54f5844d63908c6c31
3
+ size 779264
neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e796f6271a547530c9625da1ca1b5155f4d2a3d2fb51f03fbb465adfa2554c4
3
+ size 787211
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+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-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3312876ce41e0fcc32e5f19ddc83cfa44fe317d39b1f1aa97a6b21f49acbb23
3
+ size 586051
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81219ec13b4f22f03d84b7a75fa54cf308d9910802fcaff32c3be93c0486790
3
+ size 7097344
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9167b7b2cd10069c278b83192fbb62e014bb7c1eb8594c71677648de956fdfdd
3
  size 277504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c575672250d5f23841d008ced6c33f1df62b6d57923b8be0b7797455ae58cf2
3
  size 277504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b744dda98cd03803c365f911815c08eeee3aad06d05eafe96e00f28e9f06e3de
3
  size 289571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05228c5d86d72717d585b6556529ede68ef62b4a306d5d7bfaf5f07ef7d9d96
3
  size 289571
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd1ef2067eff59396cb5a741fdbf3492f2ddac863de7a34eaf042bd74be4a42d
3
  size 543744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dba7c62aa41379f9b1362ec08c4a98c7c5a74f1e99be09a8ea6d1a512a7372
3
  size 543744
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e873c37f261eb628a038c0c6b418dae07e3f575504d5b6706a5026406dc54fb
3
  size 563380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8516abb72de6f5c8d2b9ad74508eb524c404b4dbf23acc26daac265ba6925161
3
  size 563380
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9ab01e1069c448e642848435c58af0d2ca04dcd431838e16b957a63a952e1a
3
  size 277504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aac12629bb09a3f29593e822adc9258c99737b4f857e6fc1d78284fea075b5d
3
  size 277504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:331bb9d229be75ef1f6754a79bc020f2388c9c6fdb432a16f6cd667d2b94d4fe
3
  size 285854
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0772da52a0bb2b152a5ed85c72eb32f7e865604c07c0d0d40db2980016c27c
3
  size 285854
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+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-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9b6aca1e528301e8b70a85f4b3803a2da9a27aa87dee043f72da87c157254a
3
+ size 87854
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc532f4b5f8641fae558b9bc2b4047b3d2e1b7c809bc48b06cb2d5b2d6d058e8
3
+ size 400384
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28c51e6fd4b42e0588441f955581bf23565ed5a879a7e641439ae47272b0d24a
3
  size 277504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b61279642ab3f4895869ac9220451ba0253a65848a0ea4cc5f727f78970ff3f
3
  size 277504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6af229fc588092ec7a5e0ac299db07d08f1ef4b72c122bddc478afa3212d6d1
3
  size 289031
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717b264eed41092c6a186e7596770239039aa71701a44a551fae1b51b3a3fc3a
3
  size 289031
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:702e8f63de618809f7d877dbba24bcc8deb1987f3b2fdad4b94a2c0cb91dafd4
3
  size 83504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0209401219006cca96e01930250e97052c586f1267ed95762a3fd065de8cbe9
3
  size 83504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:686f0112632596b7425a069e7d88002f18a49909ec85304d459874e335339f1e
3
  size 328704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3be943131798156033b5df1ddf7aeaa12171fb23e4115c6048429dd50c9ce02
3
  size 328704
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+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-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.done ADDED
File without changes