Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
586
dacorvo HF Staff commited on
Commit
d230b9e
·
verified ·
1 Parent(s): dea607e

Synchronizing local compiler cache.

Browse files
Files changed (31) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/qwen2/Qwen/Qwen2.5-0.5B/6f381e9a0d80f3d23d0b.json +97 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/qwen2/Qwen/Qwen2.5-0.5B/a63810145b94bfcdfd0d.json +97 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/c1655182b84da2a4c42e.json +149 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/compile_flags.json +1 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.done +0 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.hlo_module.pb +3 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.neff +3 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/wrapped_neff.hlo +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/compile_flags.json +1 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.done +0 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.hlo_module.pb +3 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.neff +3 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/wrapped_neff.hlo +3 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/compile_flags.json +1 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.done +0 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.hlo_module.pb +3 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.neff +3 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/compile_flags.json +1 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.done +0 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.hlo_module.pb +3 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.neff +3 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/wrapped_neff.hlo +3 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/compile_flags.json +1 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.done +0 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.hlo_module.pb +3 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.neff +3 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/compile_flags.json +1 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.done +0 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.hlo_module.pb +3 -0
  31. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -10235,3 +10235,12 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f9ed5e3ab30730f18597+ed72d204/model.neff f
10235
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
10236
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10237
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
10235
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d8b3bbf6ba518b8162f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
10236
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10237
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa860ba18e95034cf093+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10238
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10239
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_198b5b02b387709019ea+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10240
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10241
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7076b883d5c8650d94da+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10242
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_837bdb7b4c4f834e67af+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
10243
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
10244
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_83e84045fc71578eb073+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10245
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a9ae7a29deecc8ce3b7e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
10246
+ 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.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/qwen2/Qwen/Qwen2.5-0.5B/a63810145b94bfcdfd0d.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": 32768,
62
+ "max_topk": 256,
63
+ "mlp_kernel_enabled": false,
64
+ "mlp_kernel_fuse_residual_add": false,
65
+ "n_active_tokens": 32768,
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": 32768,
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/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_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_cc4e26d5285848960dd0+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_cc4e26d5285848960dd0+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bdb4d686f27baa54f6d410dbbfeef63fd90329e44bfc5e1e8027ffa394dfd7
3
+ size 567258
neuronxcc-2.19.8089.0+8ab9f450/MODULE_cc4e26d5285848960dd0+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394132598a21a72295177dfdc3828952fab9d6d2b103429abcdbd37ce263bd80
3
+ size 2735104