Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
648
htokoyo commited on
Commit
02bc10a
·
verified ·
1 Parent(s): d78f855

Synchronizing local compiler cache.

Browse files
Files changed (20) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.1/qwen3/Qwen/Qwen3-1.7B/f70ea0969844b133f0ae.json +86 -0
  3. neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/compile_flags.json +1 -0
  4. neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.done +0 -0
  5. neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.hlo_module.pb +3 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.neff +3 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/wrapped_neff.hlo +3 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/compile_flags.json +1 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.done +0 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.hlo_module.pb +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.neff +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/compile_flags.json +1 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.done +0 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.hlo_module.pb +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.neff +3 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/compile_flags.json +1 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.done +0 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.hlo_module.pb +3 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.neff +3 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -12865,3 +12865,9 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_2350290941871099335+fad94d7c/model.neff f
12865
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_4008190147779697691+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
12866
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_5027494103159155482+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
12867
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6734169947326813850+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
12865
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_4008190147779697691+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
12866
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_5027494103159155482+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
12867
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_6734169947326813850+fad94d7c/model.neff filter=lfs diff=lfs merge=lfs -text
12868
+ neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12869
+ neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12870
+ neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
12871
+ neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
12872
+ neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12873
+ neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.1/qwen3/Qwen/Qwen3-1.7B/f70ea0969844b133f0ae.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
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": 1,
51
+ "capacity_factor": null,
52
+ "checkpoint_id": "Qwen/Qwen3-1.7B",
53
+ "checkpoint_revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
54
+ "continuous_batching": false,
55
+ "ep_degree": 1,
56
+ "fused_qkv": true,
57
+ "glu_mlp": true,
58
+ "local_ranks_size": 2,
59
+ "max_batch_size": 1,
60
+ "max_context_length": 1024,
61
+ "max_topk": 256,
62
+ "n_active_tokens": 1024,
63
+ "neuronxcc_version": "2.21.33363.0+82129205",
64
+ "on_device_sampling": true,
65
+ "optimum_neuron_version": "0.4.1",
66
+ "output_logits": false,
67
+ "pp_degree": 1,
68
+ "sequence_length": 1024,
69
+ "speculation_length": 0,
70
+ "start_rank_id": 0,
71
+ "target": "trn2",
72
+ "torch_dtype": "bfloat16",
73
+ "tp_degree": 2
74
+ },
75
+ "num_attention_heads": 16,
76
+ "num_hidden_layers": 28,
77
+ "num_key_value_heads": 8,
78
+ "rms_norm_eps": 1e-06,
79
+ "rope_scaling": null,
80
+ "rope_theta": 1000000,
81
+ "sliding_window": null,
82
+ "tie_word_embeddings": true,
83
+ "use_cache": true,
84
+ "use_sliding_window": false,
85
+ "vocab_size": 151936
86
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72c990573608123c8b24396d0825d7c39a3f5a2f3115e6d77bc79893fa85c21
3
+ size 1990432
neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb89fbc6ca8a6c2ecbd7865dc93f3ae64ff576212e19a045c45b9f9de002959
3
+ size 3687424
neuronxcc-2.21.33363.0+82129205/MODULE_3776c04776566f625e21+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a007f2f648bb41aa1461153d697d287315ab058cf045cca3af37862356caa14
3
+ size 3825515
neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2959c4c23ab71424ec6399f7bc914e4b01d82535bd16de20bb3425383a179740
3
+ size 2144464
neuronxcc-2.21.33363.0+82129205/MODULE_3f0ed90cd014ffc29453+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06cafef0b3da2d61a44bc103c195e993037c6320419c017bff6e2e2f9438a1d
3
+ size 10456064
neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f280ad29a48e78ee0865141cb9b0ea03549ed5afebab9b1784c902bea3e8f76
3
+ size 2199929
neuronxcc-2.21.33363.0+82129205/MODULE_e4f6817b6d82f5231c66+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b46b018d4b2e5b0babc92c5a4a998a2961411c9644a5ca3dad76e5a018bce25
3
+ size 9739264
neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47d5afe1f8d2efae803e6189554c95c501884a42c5a44776c13c4195dc2260e
3
+ size 1927001
neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32dd3147e6d709f43fd5c0c9482f440381c823916595cdfeec4c4ee6bad8d246
3
+ size 4117504
neuronxcc-2.21.33363.0+82129205/MODULE_fe656f3e273e10e0f566+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1eedbfc18ed3a90b386f2942361f13c3ca03cdf545359d588c08ebf564a1c3
3
+ size 4255004