Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
tengomucho HF Staff commited on
Commit
8f4c2a6
·
verified ·
1 Parent(s): 5a8f2ab

Synchronizing local compiler cache.

Browse files
Files changed (12) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/8d67a5db932b99602641.json +135 -0
  3. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/8d67a5db932b99602641.json +135 -0
  4. neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/compile_flags.json +1 -0
  5. neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.done +0 -0
  6. neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.hlo_module.pb +3 -0
  7. neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.neff +3 -0
  8. neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/compile_flags.json +1 -0
  9. neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.done +0 -0
  10. neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.hlo_module.pb +3 -0
  11. neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.neff +3 -0
  12. neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -7974,3 +7974,6 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_dad585d1d1ec4c29c81d+519f203d/model.neff f
7974
  neuronxcc-2.26.6360.0+6f180f47/MODULE_b13ab40b20254c3247e6+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text
7975
  neuronxcc-2.26.6360.0+6f180f47/MODULE_cc72ef385cb8cb0aba40+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7976
  neuronxcc-2.26.6360.0+6f180f47/MODULE_cc72ef385cb8cb0aba40+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
7974
  neuronxcc-2.26.6360.0+6f180f47/MODULE_b13ab40b20254c3247e6+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text
7975
  neuronxcc-2.26.6360.0+6f180f47/MODULE_cc72ef385cb8cb0aba40+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7976
  neuronxcc-2.26.6360.0+6f180f47/MODULE_cc72ef385cb8cb0aba40+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7977
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
7978
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7979
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/8d67a5db932b99602641.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "bfloat16",
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
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
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 65536,
54
+ "max_window_layers": 28,
55
+ "mlp_bias": false,
56
+ "model_type": "smollm3",
57
+ "neuron": {
58
+ "_serialized_key": "NxDNeuronConfig",
59
+ "batch_size": 4,
60
+ "capacity_factor": null,
61
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
62
+ "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
63
+ "continuous_batching": true,
64
+ "ep_degree": 1,
65
+ "fused_qkv": true,
66
+ "glu_mlp": true,
67
+ "local_ranks_size": 2,
68
+ "max_batch_size": 4,
69
+ "max_context_length": 1024,
70
+ "max_topk": 256,
71
+ "n_active_tokens": 1024,
72
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
73
+ "on_device_sampling": true,
74
+ "optimum_neuron_version": "0.4.7.dev0",
75
+ "output_logits": false,
76
+ "pp_degree": 1,
77
+ "prefill_chunk_size": 0,
78
+ "sequence_length": 1024,
79
+ "speculation_length": 0,
80
+ "start_rank_id": 0,
81
+ "target": "trn1",
82
+ "torch_dtype": "bfloat16",
83
+ "tp_degree": 2
84
+ },
85
+ "no_rope_layer_interval": 4,
86
+ "no_rope_layers": [
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 0,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 0,
95
+ 1,
96
+ 1,
97
+ 1,
98
+ 0,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 0,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 0,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 0,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 0,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 0,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 0
123
+ ],
124
+ "num_attention_heads": 16,
125
+ "num_hidden_layers": 36,
126
+ "num_key_value_heads": 4,
127
+ "pretraining_tp": 2,
128
+ "rms_norm_eps": 1e-06,
129
+ "rope_scaling": null,
130
+ "rope_theta": 5000000.0,
131
+ "sliding_window": null,
132
+ "use_cache": false,
133
+ "use_sliding_window": false,
134
+ "vocab_size": 128256
135
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/8d67a5db932b99602641.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "bfloat16",
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
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
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 65536,
54
+ "max_window_layers": 28,
55
+ "mlp_bias": false,
56
+ "model_type": "smollm3",
57
+ "neuron": {
58
+ "_serialized_key": "NxDNeuronConfig",
59
+ "batch_size": 4,
60
+ "capacity_factor": null,
61
+ "checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
62
+ "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
63
+ "continuous_batching": true,
64
+ "ep_degree": 1,
65
+ "fused_qkv": true,
66
+ "glu_mlp": true,
67
+ "local_ranks_size": 2,
68
+ "max_batch_size": 4,
69
+ "max_context_length": 1024,
70
+ "max_topk": 256,
71
+ "n_active_tokens": 1024,
72
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
73
+ "on_device_sampling": true,
74
+ "optimum_neuron_version": "0.4.7.dev0",
75
+ "output_logits": false,
76
+ "pp_degree": 1,
77
+ "prefill_chunk_size": 0,
78
+ "sequence_length": 1024,
79
+ "speculation_length": 0,
80
+ "start_rank_id": 0,
81
+ "target": "trn1",
82
+ "torch_dtype": "bfloat16",
83
+ "tp_degree": 2
84
+ },
85
+ "no_rope_layer_interval": 4,
86
+ "no_rope_layers": [
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 0,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 0,
95
+ 1,
96
+ 1,
97
+ 1,
98
+ 0,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 0,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 0,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 0,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 0,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 0,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 0
123
+ ],
124
+ "num_attention_heads": 16,
125
+ "num_hidden_layers": 36,
126
+ "num_key_value_heads": 4,
127
+ "pretraining_tp": 2,
128
+ "rms_norm_eps": 1e-06,
129
+ "rope_scaling": null,
130
+ "rope_theta": 5000000.0,
131
+ "sliding_window": null,
132
+ "use_cache": false,
133
+ "use_sliding_window": false,
134
+ "vocab_size": 128256
135
+ }
neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+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_2a3e386367db70e3fc2b+519f203d/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a701ba04823124d41047676fac2da86dfa7b57e78a7813b8f3fb16dd94d2cb
3
+ size 2645928
neuronxcc-2.26.6360.0+6f180f47/MODULE_2a3e386367db70e3fc2b+519f203d/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cc00d48efdb33702f223eb8446dc3dcc1e3f7c2b0965244c053ee957bd2481
3
+ size 2868224
neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+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_c4ae95f071c0848efcb3+84337dd9/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d45e85a93a7e9445a7e550651f43fdada00806819a873fc77297b16bd30db28
3
+ size 3007200
neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6ca93ecea4db0d6a2ccd0c8755fc790706eaccb08bf77b36b706dde5d3fc9b
3
+ size 5295104
neuronxcc-2.26.6360.0+6f180f47/MODULE_c4ae95f071c0848efcb3+84337dd9/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6755a36b2cdbed04f827832e007b1f8ac4c7bfe79f251aed4558a1945161a3
3
+ size 5461628