Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
9b6b42b
·
verified ·
1 Parent(s): b822bd7

Synchronizing local compiler cache.

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/e2ed8bb10bb9bb8b2905.json +88 -0
  3. neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/e2ed8bb10bb9bb8b2905.json +88 -0
  4. neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/compile_flags.json +1 -0
  5. neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.done +0 -0
  6. neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.hlo_module.pb +3 -0
  7. neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.neff +3 -0
.gitattributes CHANGED
@@ -7337,3 +7337,4 @@ neuronxcc-2.23.6484.0+3b612583/MODULE_c554dcf79d6b43ffcf54+84337dd9/wrapped_neff
7337
  neuronxcc-2.23.6484.0+3b612583/MODULE_4dc8308e20796dc6f7a5+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
7338
  neuronxcc-2.23.6484.0+3b612583/MODULE_b64a1f9e4423dce4e8f3+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7339
  neuronxcc-2.23.6484.0+3b612583/MODULE_b64a1f9e4423dce4e8f3+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
7337
  neuronxcc-2.23.6484.0+3b612583/MODULE_4dc8308e20796dc6f7a5+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
7338
  neuronxcc-2.23.6484.0+3b612583/MODULE_b64a1f9e4423dce4e8f3+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
7339
  neuronxcc-2.23.6484.0+3b612583/MODULE_b64a1f9e4423dce4e8f3+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7340
+ neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/e2ed8bb10bb9bb8b2905.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "feature-extraction",
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": false,
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": "2.23.6484.0+3b612583",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.6.dev3",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "prefill_chunk_size": 1024,
70
+ "sequence_length": 8192,
71
+ "speculation_length": 0,
72
+ "start_rank_id": 0,
73
+ "target": "trn1",
74
+ "torch_dtype": "bfloat16",
75
+ "tp_degree": 2
76
+ },
77
+ "num_attention_heads": 16,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 8,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": null,
82
+ "rope_theta": 1000000,
83
+ "sliding_window": null,
84
+ "tie_word_embeddings": true,
85
+ "use_cache": true,
86
+ "use_sliding_window": false,
87
+ "vocab_size": 151669
88
+ }
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/e2ed8bb10bb9bb8b2905.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-Embedding-0.6B",
4
+ "_task": "feature-extraction",
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": false,
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": "2.23.6484.0+3b612583",
65
+ "on_device_sampling": false,
66
+ "optimum_neuron_version": "0.4.6.dev3",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "prefill_chunk_size": 1024,
70
+ "sequence_length": 8192,
71
+ "speculation_length": 0,
72
+ "start_rank_id": 0,
73
+ "target": "trn1",
74
+ "torch_dtype": "bfloat16",
75
+ "tp_degree": 2
76
+ },
77
+ "num_attention_heads": 16,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 8,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": null,
82
+ "rope_theta": 1000000,
83
+ "sliding_window": null,
84
+ "tie_word_embeddings": true,
85
+ "use_cache": true,
86
+ "use_sliding_window": false,
87
+ "vocab_size": 151669
88
+ }
neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/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/encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.done ADDED
File without changes
neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670bd70e97d7b789468bbfc44c9decbe0daae4bb96732ff1797400fa2b98155a
3
+ size 1679371
neuronxcc-2.23.6484.0+3b612583/MODULE_865bee4df11d5919ca3f+97496b47/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbff061451c13adfa0ee69cdb238ab761c7e75746ad3289cf1d4ac45f5b7b7e
3
+ size 29860864