Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
3cfbc9e
·
verified ·
1 Parent(s): ba566e9

Synchronizing local compiler cache.

Browse files
Files changed (15) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/f28827ac20434fbe0ad8.json +135 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/f28827ac20434fbe0ad8.json +135 -0
  4. neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/compile_flags.json +1 -0
  5. neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.done +0 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.hlo_module.pb +3 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.neff +3 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/compile_flags.json +1 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.done +0 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.neff +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/wrapped_neff.hlo +3 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/compile_flags.json +1 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/model.hlo_module.pb +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/model.log +1 -0
.gitattributes CHANGED
@@ -7129,3 +7129,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/wrapped_nef
7129
  neuronxcc-2.21.33363.0+82129205/MODULE_5006ac810070ead7ed92+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
7130
  neuronxcc-2.21.33363.0+82129205/MODULE_a1d5b9d5676277a73661+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7131
  neuronxcc-2.21.33363.0+82129205/MODULE_a1d5b9d5676277a73661+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
7129
  neuronxcc-2.21.33363.0+82129205/MODULE_5006ac810070ead7ed92+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
7130
  neuronxcc-2.21.33363.0+82129205/MODULE_a1d5b9d5676277a73661+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7131
  neuronxcc-2.21.33363.0+82129205/MODULE_a1d5b9d5676277a73661+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7132
+ neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
7133
+ neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7134
+ neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/f28827ac20434fbe0ad8.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": "2.21.33363.0+82129205",
73
+ "on_device_sampling": true,
74
+ "optimum_neuron_version": "0.4.6.dev2",
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-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/f28827ac20434fbe0ad8.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": "2.21.33363.0+82129205",
73
+ "on_device_sampling": true,
74
+ "optimum_neuron_version": "0.4.6.dev2",
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-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/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/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990cedcdabb6c3f81555756a62bf720aa67bcf902b798c5bc0ecb2cb1ec99630
3
+ size 839610
neuronxcc-2.21.33363.0+82129205/MODULE_c68ed9d0d3211fb37165+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1fde40d64ad7a1680d0f7140de088850a187367b1d9d807c4a6cce6049608d9
3
+ size 12626944
neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179bdac81143630f9d441635b2b26fa7932ed558003eca339746b0003a725b51
3
+ size 904767
neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37fc84e549c108bc966313a5725202957b82812292828925d342489eb7729b4
3
+ size 5827584
neuronxcc-2.21.33363.0+82129205/MODULE_d50f09930f3886ac4b66+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fef7123c53ed6ad89406099987d3e6d38e26878221cb72cd5cedfb1903467a0
3
+ size 5994108
neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d62b0089ca06aace851336de76d8714df772fc1fd25f2fb6cccca122c1411c0
3
+ size 1538064
neuronxcc-2.21.33363.0+82129205/MODULE_da7543b73fbd9c77b695+6170d8e1/model.log ADDED
@@ -0,0 +1 @@
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/chunked_prefill/_tp0_bk0/model.MODULE_da7543b73fbd9c77b695+6170d8e1.hlo_module.pb', '--output', '/tmp/nxd_model/chunked_prefill/_tp0_bk0/model.MODULE_da7543b73fbd9c77b695+6170d8e1.neff', '--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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: