Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
3162d3e
·
verified ·
1 Parent(s): c98abbf

Synchronizing local compiler cache.

Browse files
Files changed (22) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0438c23a5711521d23f3885ee2d8467e2cafd830d3f9b67032189f97374cc4c0/66a3c3fbb092fd0b22b4.json +88 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-1.7B/66a3c3fbb092fd0b22b4.json +88 -0
  4. neuronxcc-2.21.33363.0+82129205/MODULE_1759fced9dd9a678973e+24129607/model.hlo_module.pb +1 -1
  5. neuronxcc-2.21.33363.0+82129205/MODULE_1759fced9dd9a678973e+24129607/model.neff +1 -1
  6. neuronxcc-2.21.33363.0+82129205/MODULE_4ff804c2533da46e613e+24129607/model.hlo_module.pb +1 -1
  7. neuronxcc-2.21.33363.0+82129205/MODULE_4ff804c2533da46e613e+24129607/model.neff +1 -1
  8. neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/model.hlo_module.pb +1 -1
  9. neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/model.neff +1 -1
  10. neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/wrapped_neff.hlo +1 -1
  11. neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/model.hlo_module.pb +1 -1
  12. neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/model.neff +1 -1
  13. neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/wrapped_neff.hlo +1 -1
  14. neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/compile_flags.json +1 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.done +0 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.hlo_module.pb +3 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.neff +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/compile_flags.json +1 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.done +0 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.hlo_module.pb +3 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.neff +3 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -7774,3 +7774,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_cad34e8b42cec5152517+a02c3a36/wrapped_nef
7774
  neuronxcc-2.21.33363.0+82129205/MODULE_6781be5fc2d8529ad204+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7775
  neuronxcc-2.21.33363.0+82129205/MODULE_6781be5fc2d8529ad204+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7776
  neuronxcc-2.21.33363.0+82129205/MODULE_f100cf6bbe2c168dffc8+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
7774
  neuronxcc-2.21.33363.0+82129205/MODULE_6781be5fc2d8529ad204+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7775
  neuronxcc-2.21.33363.0+82129205/MODULE_6781be5fc2d8529ad204+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7776
  neuronxcc-2.21.33363.0+82129205/MODULE_f100cf6bbe2c168dffc8+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
7777
+ neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
7778
+ neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
7779
+ neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0438c23a5711521d23f3885ee2d8467e2cafd830d3f9b67032189f97374cc4c0/66a3c3fbb092fd0b22b4.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-1.7B",
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": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
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": 40960,
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/Qwen3-1.7B",
54
+ "checkpoint_revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
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": 1024,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 1024,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
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": 0,
70
+ "sequence_length": 1024,
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": 151936
88
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-1.7B/66a3c3fbb092fd0b22b4.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-1.7B",
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": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
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": 40960,
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/Qwen3-1.7B",
54
+ "checkpoint_revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
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": 1024,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 1024,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
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": 0,
70
+ "sequence_length": 1024,
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": 151936
88
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_1759fced9dd9a678973e+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8223a0880f04437df80f89de1868b68be53988eb9a109c31fbf2423e0595ab55
3
  size 684041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b12e4bc9a9646f83987e5eb925b237f68f4d7a5569ef4a101e91e22748bfcb6
3
  size 684041
neuronxcc-2.21.33363.0+82129205/MODULE_1759fced9dd9a678973e+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:716d2d5bdbafb617fe64ce7e95b970d04f7da3600f9ea8defbaecd511d634961
3
  size 7732224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a849a1d1b254aef58958b0a532465d7fd2588408c54ce33e87d87c11fb2871cc
3
  size 7732224
neuronxcc-2.21.33363.0+82129205/MODULE_4ff804c2533da46e613e+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77aa6e56466f63a602dedff46d9989619913f612654147b3c637f7d3de61f7bb
3
  size 1050679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868cca689a34e99963ba4838928c3d05b3b7ff0c504770b6e3b057f912c499df
3
  size 1050679
neuronxcc-2.21.33363.0+82129205/MODULE_4ff804c2533da46e613e+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34a2c883e2aa715e151451bee73497a2f06cc46696d7df7deaa3002177def80f
3
  size 14050304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7092c426f768f52ed7be2a5ae675118ff348d21dc203e5a969ad6da48a833fb0
3
  size 14050304
neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c2a0e27aea45eec39afceeccd973f758e74d7f2b39164586a4bd50817a82017
3
  size 1117688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e7fcdf9f65af1b99f353b41bfb54288571325ca47b98d54e3e989a576ff880
3
  size 1117688
neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1a407e255505988a25235719e0362bc0b25a57529345a8e1a677f7e3958cd16
3
  size 5387264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f3a621f39fe257c700d6bfc0b4b4ab251957d63970b10bb8ecf19501d9f36a
3
  size 5387264
neuronxcc-2.21.33363.0+82129205/MODULE_5742ef8f5910f4e17377+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:134d868a2ff9c32bba7e5cee35716ccddbe5d981756fb94db39373e8bbae9aa9
3
  size 5571457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c0c9873fdc5c05d11f5911176dcef5b6049e8a5c619cd4e51ed757c641e98e
3
  size 5571457
neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a344a8bfb0bd70d150a25d375f0a7ad1432403ec9c9a9455db46debc4a8e84eb
3
  size 727217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97aecb8c044acc0ebbfea336087df614b77fd28df2dfa780403927456239a624
3
  size 727217
neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25bc5e849b16d05bd4e3955ff08c5681b576bef793e02c4e34a4578f4a537922
3
  size 3472384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8768b115e2249ec808a67cd0136f0169269ce5e8186bbae6a46c21db2c0594
3
  size 3472384
neuronxcc-2.21.33363.0+82129205/MODULE_88833531cb6c582d4830+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8145a60228c00cae89502e7d9814a447a7f0719dc42e45698b88165002e717a
3
  size 3610166
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf0374f79f6879ee32742c88e40cd6578de4b103c9b299baea56cb034b5e7ab
3
  size 3610166
neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+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_a331727721baf5338bd6+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05c45b47b083316842dde59e5c5d53ed0e1b15b02795cb9e9bba7c01d2111f0
3
+ size 693336
neuronxcc-2.21.33363.0+82129205/MODULE_a331727721baf5338bd6+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76af68f33960b293cf666eecb8a0c32adae5d8b933d8bf806756bd45f034c679
3
+ size 8377344
neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+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_b12885ed4bcc4569c145+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d9b3da24f5ae4b7855e7e633f93a202e796cafa3585056f3143ea4bcfa7971
3
+ size 735532
neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cd3ee8a3cf1659f6a37c969a92a3ada8cfbb164446fc666a14f24f02cf47fc
3
+ size 3615744
neuronxcc-2.21.33363.0+82129205/MODULE_b12885ed4bcc4569c145+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae222edb0eb9f90fda1c6a7e4e5816080438d4b74696b706c114682e7f4a91ea
3
+ size 3752605