Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
b56f4e7
·
verified ·
1 Parent(s): c5f5264

Synchronizing local compiler cache.

Browse files
Files changed (19) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev1/4d281af1651143f9a83b42af25d9f0a533dbbd9c3441537127ae772fd3e399cc/e14467c71bee5cf6b4df.json +87 -0
  3. neuronxcc-2.21.33363.0+82129205/MODULE_0a5cbcb0f0d605182b40+24129607/compile_flags.json +1 -0
  4. neuronxcc-2.21.33363.0+82129205/MODULE_0a5cbcb0f0d605182b40+24129607/model.hlo_module.pb +3 -0
  5. neuronxcc-2.21.33363.0+82129205/MODULE_0a5cbcb0f0d605182b40+24129607/model.log +1 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/compile_flags.json +1 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.done +0 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.hlo_module.pb +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.neff +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/wrapped_neff.hlo +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/compile_flags.json +1 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.done +0 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.neff +3 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -6281,3 +6281,8 @@ neuronxcc-2.21.33363.0+82129205/MODULE_4cf1e5f6e4c17bb56bb0+a02c3a36/wrapped_nef
6281
  neuronxcc-2.21.33363.0+82129205/MODULE_27dcb29f0a28b1d6f51e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6282
  neuronxcc-2.21.33363.0+82129205/MODULE_27dcb29f0a28b1d6f51e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6283
  neuronxcc-2.21.33363.0+82129205/MODULE_dd01d7a2913cbd8c1ba1+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
6281
  neuronxcc-2.21.33363.0+82129205/MODULE_27dcb29f0a28b1d6f51e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6282
  neuronxcc-2.21.33363.0+82129205/MODULE_27dcb29f0a28b1d6f51e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6283
  neuronxcc-2.21.33363.0+82129205/MODULE_dd01d7a2913cbd8c1ba1+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6284
+ neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6285
+ neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6286
+ neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6287
+ neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6288
+ neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev1/4d281af1651143f9a83b42af25d9f0a533dbbd9c3441537127ae772fd3e399cc/e14467c71bee5cf6b4df.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
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
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
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 4,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
54
+ "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
55
+ "continuous_batching": true,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 2,
60
+ "max_batch_size": 4,
61
+ "max_context_length": 8192,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 8192,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.5.dev1",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 8192,
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": 151669
87
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_0a5cbcb0f0d605182b40+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_0a5cbcb0f0d605182b40+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6460ecb77b0df76fab544cee5f5c477229fd70e65cd0377841933f5251ae36
3
+ size 1134023
neuronxcc-2.21.33363.0+82129205/MODULE_0a5cbcb0f0d605182b40+24129607/model.log ADDED
@@ -0,0 +1 @@
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_0a5cbcb0f0d605182b40+24129607.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_0a5cbcb0f0d605182b40+24129607.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/context_encoding/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']:
neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+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_0e8f2cac7949cfdcbe7c+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2480c10b0a667a77bc9f969b614c1c1627c7c0b72a47251ae70598baa2b8ef8c
3
+ size 1160172
neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd6a56a6d6d101f9dc7e21594bc27ca343f95faa1e79f666426a8bc49de066f
3
+ size 5274624
neuronxcc-2.21.33363.0+82129205/MODULE_0e8f2cac7949cfdcbe7c+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1965465ca9aae5d3723f6c6e5eb6986498f071af8bc72caec566f9e9dab8a8e8
3
+ size 5411681
neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+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_79eb3abf001c934aa416+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22a67788c464a4c8d78838646a5854fad916f6fcb96004c989a7eb5af67c0ed
3
+ size 1305951
neuronxcc-2.21.33363.0+82129205/MODULE_79eb3abf001c934aa416+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3514df74437731caf4111758f70df12219b13b0cad80b4a75dda72ab95a1b3
3
+ size 98520064
neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+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_b8bea2e3eb787b70e571+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4894daa7a63700186ae52e4113ba44c70532da051fb907e0293a1513b4a005f1
3
+ size 1145836
neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2af732b831da9ea85f28b840e50fa705fcf0d534e6f97ec96dc3beec36e570
3
+ size 2264064
neuronxcc-2.21.33363.0+82129205/MODULE_b8bea2e3eb787b70e571+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c7546b02538f526325b31b714578c301662ec58038e6d18f9c0d2ccbe48da6
3
+ size 2401121