Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
1c50d3f
·
verified ·
1 Parent(s): 1d630ca

Synchronizing local compiler cache.

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/qwen3/Qwen/Qwen3-0.6B/e2e6df4e0d01752ba5dc.json +89 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/compile_flags.json +1 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.done +0 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.hlo_module.pb +3 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -4499,3 +4499,4 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_e905becff9d80249a7ae+e4474b78/wrapped_neff
4499
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d618b5f6d6f813b7449+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4500
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_158c2b755daab1e740a8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4501
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb8c372007f461bd6f30+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
4499
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d618b5f6d6f813b7449+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4500
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_158c2b755daab1e740a8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4501
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb8c372007f461bd6f30+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
4502
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/qwen3/Qwen/Qwen3-0.6B/e2e6df4e0d01752ba5dc.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
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
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "neuron": {
49
+ "_serialized_key": "NxDNeuronConfig",
50
+ "batch_size": 4,
51
+ "capacity_factor": null,
52
+ "cc_pipeline_tiling_factor": 2,
53
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
54
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
55
+ "continuous_batching": true,
56
+ "enable_bucketing": false,
57
+ "ep_degree": 1,
58
+ "fused_qkv": true,
59
+ "glu_mlp": true,
60
+ "local_ranks_size": 2,
61
+ "logical_nc_config": 1,
62
+ "max_batch_size": 4,
63
+ "max_context_length": 4096,
64
+ "max_topk": 256,
65
+ "n_active_tokens": 4096,
66
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
67
+ "on_device_sampling": false,
68
+ "optimum_neuron_version": "0.3.1.dev5",
69
+ "output_logits": false,
70
+ "pp_degree": 1,
71
+ "sequence_length": 4096,
72
+ "speculation_length": 0,
73
+ "start_rank_id": 0,
74
+ "target": null,
75
+ "torch_dtype": "bfloat16",
76
+ "tp_degree": 2
77
+ },
78
+ "num_attention_heads": 16,
79
+ "num_hidden_layers": 28,
80
+ "num_key_value_heads": 8,
81
+ "rms_norm_eps": 1e-06,
82
+ "rope_scaling": null,
83
+ "rope_theta": 1000000,
84
+ "sliding_window": null,
85
+ "tie_word_embeddings": true,
86
+ "use_cache": true,
87
+ "use_sliding_window": false,
88
+ "vocab_size": 151936
89
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+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_6e8eed42076f4bade3b5+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f580b7a4fa38040a204b081a8509dbbdf2111fc26fc68dc3114d763744a711
3
+ size 685704
neuronxcc-2.19.8089.0+8ab9f450/MODULE_6e8eed42076f4bade3b5+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6630e7b79950067ee403a77b657665ae30401840c4372bf77ae9754c26438b7
3
+ size 20849664