Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
tengomucho HF Staff commited on
Commit
c087ebc
·
verified ·
1 Parent(s): 98f0347

Synchronizing local compiler cache.

Browse files
Files changed (17) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0a07fcbaaaca6e450fabdb638553525f4bfb07bcac85320ca02556f31cd98cf/68b8b60ad74d23a1ba59.json +130 -0
  3. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/unsloth/gemma-3-4b-it/68b8b60ad74d23a1ba59.json +130 -0
  4. neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/compile_flags.json +1 -0
  5. neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.done +0 -0
  6. neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.hlo_module.pb +3 -0
  7. neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.neff +3 -0
  8. neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/wrapped_neff.hlo +3 -0
  9. neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/compile_flags.json +1 -0
  10. neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.done +0 -0
  11. neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.hlo_module.pb +3 -0
  12. neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.neff +3 -0
  13. neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/wrapped_neff.hlo +3 -0
  14. neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/compile_flags.json +1 -0
  15. neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.done +0 -0
  16. neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.hlo_module.pb +3 -0
  17. neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.neff +3 -0
.gitattributes CHANGED
@@ -7980,3 +7980,8 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/wrapped_neff
7980
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8d2d1883faa73ace1fd9+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text
7981
  neuronxcc-2.26.6360.0+6f180f47/MODULE_bc2e43a022ce63930953+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7982
  neuronxcc-2.26.6360.0+6f180f47/MODULE_bc2e43a022ce63930953+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
7980
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8d2d1883faa73ace1fd9+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text
7981
  neuronxcc-2.26.6360.0+6f180f47/MODULE_bc2e43a022ce63930953+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7982
  neuronxcc-2.26.6360.0+6f180f47/MODULE_bc2e43a022ce63930953+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7983
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7984
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7985
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text
7986
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7987
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0a07fcbaaaca6e450fabdb638553525f4bfb07bcac85320ca02556f31cd98cf/68b8b60ad74d23a1ba59.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/gemma-3-4b-it",
4
+ "_task": "image-text-to-text",
5
+ "architectures": [
6
+ "Gemma3ForConditionalGeneration"
7
+ ],
8
+ "boi_token_index": 255999,
9
+ "dtype": "bfloat16",
10
+ "eoi_token_index": 256000,
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "neuron": {
16
+ "_serialized_key": "NxDVLMNeuronConfig",
17
+ "batch_size": 2,
18
+ "capacity_factor": null,
19
+ "checkpoint_id": "unsloth/gemma-3-4b-it",
20
+ "checkpoint_revision": "bf46152c47f5dd20b896357cb51abc4c03b8ee8c",
21
+ "continuous_batching": true,
22
+ "ep_degree": 1,
23
+ "fused_qkv": true,
24
+ "glu_mlp": true,
25
+ "image_seq_len": 256,
26
+ "image_size": 896,
27
+ "local_ranks_size": 2,
28
+ "max_batch_size": 2,
29
+ "max_context_length": 2048,
30
+ "max_num_images": 5,
31
+ "max_topk": 256,
32
+ "n_active_tokens": 2048,
33
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
34
+ "on_device_sampling": true,
35
+ "optimum_neuron_version": "0.4.7.dev0",
36
+ "output_logits": false,
37
+ "pp_degree": 1,
38
+ "prefill_chunk_size": 0,
39
+ "sequence_length": 2048,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "text_config": {
47
+ "_sliding_window_pattern": 6,
48
+ "attention_bias": false,
49
+ "attention_dropout": 0.0,
50
+ "attn_logit_softcapping": null,
51
+ "cache_implementation": "hybrid",
52
+ "dtype": "bfloat16",
53
+ "final_logit_softcapping": null,
54
+ "head_dim": 256,
55
+ "hidden_activation": "gelu_pytorch_tanh",
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 10240,
59
+ "layer_types": [
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "full_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention"
94
+ ],
95
+ "max_position_embeddings": 131072,
96
+ "model_type": "gemma3_text",
97
+ "num_attention_heads": 8,
98
+ "num_hidden_layers": 34,
99
+ "num_key_value_heads": 4,
100
+ "query_pre_attn_scalar": 256,
101
+ "rms_norm_eps": 1e-06,
102
+ "rope_local_base_freq": 10000.0,
103
+ "rope_scaling": {
104
+ "factor": 8.0,
105
+ "rope_type": "linear"
106
+ },
107
+ "rope_theta": 1000000.0,
108
+ "sliding_window": 1024,
109
+ "sliding_window_pattern": 6,
110
+ "use_bidirectional_attention": false,
111
+ "use_cache": true,
112
+ "vocab_size": 262208
113
+ },
114
+ "unsloth_fixed": true,
115
+ "vision_config": {
116
+ "attention_dropout": 0.0,
117
+ "dtype": "bfloat16",
118
+ "hidden_act": "gelu_pytorch_tanh",
119
+ "hidden_size": 1152,
120
+ "image_size": 896,
121
+ "intermediate_size": 4304,
122
+ "layer_norm_eps": 1e-06,
123
+ "model_type": "siglip_vision_model",
124
+ "num_attention_heads": 16,
125
+ "num_channels": 3,
126
+ "num_hidden_layers": 27,
127
+ "patch_size": 14,
128
+ "vision_use_head": false
129
+ }
130
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/unsloth/gemma-3-4b-it/68b8b60ad74d23a1ba59.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/gemma-3-4b-it",
4
+ "_task": "image-text-to-text",
5
+ "architectures": [
6
+ "Gemma3ForConditionalGeneration"
7
+ ],
8
+ "boi_token_index": 255999,
9
+ "dtype": "bfloat16",
10
+ "eoi_token_index": 256000,
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "neuron": {
16
+ "_serialized_key": "NxDVLMNeuronConfig",
17
+ "batch_size": 2,
18
+ "capacity_factor": null,
19
+ "checkpoint_id": "unsloth/gemma-3-4b-it",
20
+ "checkpoint_revision": "bf46152c47f5dd20b896357cb51abc4c03b8ee8c",
21
+ "continuous_batching": true,
22
+ "ep_degree": 1,
23
+ "fused_qkv": true,
24
+ "glu_mlp": true,
25
+ "image_seq_len": 256,
26
+ "image_size": 896,
27
+ "local_ranks_size": 2,
28
+ "max_batch_size": 2,
29
+ "max_context_length": 2048,
30
+ "max_num_images": 5,
31
+ "max_topk": 256,
32
+ "n_active_tokens": 2048,
33
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
34
+ "on_device_sampling": true,
35
+ "optimum_neuron_version": "0.4.7.dev0",
36
+ "output_logits": false,
37
+ "pp_degree": 1,
38
+ "prefill_chunk_size": 0,
39
+ "sequence_length": 2048,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "text_config": {
47
+ "_sliding_window_pattern": 6,
48
+ "attention_bias": false,
49
+ "attention_dropout": 0.0,
50
+ "attn_logit_softcapping": null,
51
+ "cache_implementation": "hybrid",
52
+ "dtype": "bfloat16",
53
+ "final_logit_softcapping": null,
54
+ "head_dim": 256,
55
+ "hidden_activation": "gelu_pytorch_tanh",
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 10240,
59
+ "layer_types": [
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "full_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention"
94
+ ],
95
+ "max_position_embeddings": 131072,
96
+ "model_type": "gemma3_text",
97
+ "num_attention_heads": 8,
98
+ "num_hidden_layers": 34,
99
+ "num_key_value_heads": 4,
100
+ "query_pre_attn_scalar": 256,
101
+ "rms_norm_eps": 1e-06,
102
+ "rope_local_base_freq": 10000.0,
103
+ "rope_scaling": {
104
+ "factor": 8.0,
105
+ "rope_type": "linear"
106
+ },
107
+ "rope_theta": 1000000.0,
108
+ "sliding_window": 1024,
109
+ "sliding_window_pattern": 6,
110
+ "use_bidirectional_attention": false,
111
+ "use_cache": true,
112
+ "vocab_size": 262208
113
+ },
114
+ "unsloth_fixed": true,
115
+ "vision_config": {
116
+ "attention_dropout": 0.0,
117
+ "dtype": "bfloat16",
118
+ "hidden_act": "gelu_pytorch_tanh",
119
+ "hidden_size": 1152,
120
+ "image_size": 896,
121
+ "intermediate_size": 4304,
122
+ "layer_norm_eps": 1e-06,
123
+ "model_type": "siglip_vision_model",
124
+ "num_attention_heads": 16,
125
+ "num_channels": 3,
126
+ "num_hidden_layers": 27,
127
+ "patch_size": 14,
128
+ "vision_use_head": false
129
+ }
130
+ }
neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca73e5500db852488eb30b77de9a181e6e319c6495dae8c9afc5e094577b84e
3
+ size 3477072
neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e948ad900e1f09e579f19ddb893e4b4935877aca7f7c811a942c9a3095b612a
3
+ size 6657024
neuronxcc-2.26.6360.0+6f180f47/MODULE_346006500bc32ee87aa4+84337dd9/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c7a1eb84ae9ec068bfba69bdc1f3a94822c14865f2737897a771a7e1e54764
3
+ size 6887798
neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/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", "--verbose=35", "--logfile=/tmp/nxd_model/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0881f8c65ec694e3581f0b482fe44714b79e77b12aa7361eabc9ff74cad23f51
3
+ size 1810657
neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c261f5c272547757c6baeddefdd66b126b3e74766a7eb1ea79561744924463d4
3
+ size 22918144
neuronxcc-2.26.6360.0+6f180f47/MODULE_9e3bf0ec2a8021be8d27+1d5aa319/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7349f4f060e7b3bd0a3bfee9bb8614ce5ec277aed3ba9a188bb706a5b4758c18
3
+ size 23151262
neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592bf8647a9ce7e876f2d59b02a98cacec00c6139a6dea63f5183c20a43cd587
3
+ size 3261676
neuronxcc-2.26.6360.0+6f180f47/MODULE_bc570e0bacfe4b69cb27+519f203d/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1f0ac5107c3209900c26598e2dbc6a6b9d305905b89359a40edbc0c9931f70
3
+ size 5069824