Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
tengomucho HF Staff commited on
Commit
63eb88d
·
verified ·
1 Parent(s): 1a09bbb

Synchronizing local compiler cache.

Browse files
Files changed (28) hide show
  1. .gitattributes +8 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0/qwen2/Qwen/Qwen2.5-0.5B/f4f7271f4cc63b57e077.json +71 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/compile_flags.json +1 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.done +0 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.hlo_module.pb +3 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.neff +3 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/compile_flags.json +1 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.done +0 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.hlo_module.pb +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.neff +3 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/wrapped_neff.hlo +3 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/compile_flags.json +1 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.done +0 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.hlo_module.pb +3 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.neff +3 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/compile_flags.json +1 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.done +0 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.hlo_module.pb +3 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.neff +3 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/wrapped_neff.hlo +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/compile_flags.json +1 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.done +0 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.hlo_module.pb +3 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.neff +3 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/compile_flags.json +1 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.done +0 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.hlo_module.pb +3 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -3708,3 +3708,11 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4637147670044247985+e30acd3a/model.neff fi
3708
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_6559760091786342695+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
3709
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_7095b61940c7e3c6fe2a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3710
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_7095b61940c7e3c6fe2a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
3708
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_6559760091786342695+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text
3709
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_7095b61940c7e3c6fe2a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3710
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_7095b61940c7e3c6fe2a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3711
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3712
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3713
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3714
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3715
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3716
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3717
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3718
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0/qwen2/Qwen/Qwen2.5-0.5B/f4f7271f4cc63b57e077.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
24
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
25
+ "continuous_batching": true,
26
+ "enable_bucketing": false,
27
+ "ep_degree": 1,
28
+ "flash_decoding_enabled": false,
29
+ "fused_qkv": false,
30
+ "glu_mlp": true,
31
+ "is_chunked_prefill": false,
32
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 4,
35
+ "max_context_length": 4096,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 4096,
40
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.3.0",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 4096,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 14,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 32768,
66
+ "tie_word_embeddings": true,
67
+ "use_cache": true,
68
+ "use_mrope": false,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ab9961eb7fe4a25b47a3b18803373f33459c34ac5617af9c4c7781e30fa0b8
3
+ size 69051
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4f57ecfb36696160c651+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5751db9b31d15d14a759919bc35f02ce3ff63aeda9358e2ef22eff4877c841
3
+ size 1168384
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d6ee497ce197b05340f8c36c5be8f898ddede9b656a39274da981c27791afb
3
+ size 417088
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed920cf134cbdadbb50a7632f122d7a8c0323ba21e9eb0dc8ccc18a5a317301
3
+ size 2233344
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5458e98df48e8025667f+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f58688f8f908872822123f6925f30c56fb16144b259e3e4f79071237c831247
3
+ size 2303088
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d1b2300a6849fc6d67a4599c8d0f18126c49c27156730120f9ac0dd29260ba
3
+ size 149912
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae03fb73960b81a5271e+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c12aeebfa3297558613ee5077a653e70269c211483ab073dc571a9e9e79a6e
3
+ size 594944
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a90beaf96dcfd4b4585f63c1b023be53df6e66ea55bb31cd9adf0df5ed89cf
3
+ size 582901
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b8321042e0d06c109404b7942dcca4d5a9efda97d2199378b02f62e482c8b0
3
+ size 1444864
neuronxcc-2.19.8089.0+8ab9f450/MODULE_c28d7dd9d5c6a73b523d+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6929a4551fa51c6f11e658f7014888000f68e0768a054c38377f55972d4a46e8
3
+ size 1589775
neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+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_cdfa4acdcb97ce7c656b+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14651da2340606cbacf1238d1d63a52350255568859bdeac59fbb268dbf70a1f
3
+ size 497731
neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdfa4acdcb97ce7c656b+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cfd81ed96a51bc8c3a46b0a3e046f48ee4021c2808250ba5c0ecaf38d1301c
3
+ size 31345664
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+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_f353ef49a5c69cb68978+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1a9fa2829b02683168e9ca002cf2a1828b85f82def72e4a3f64f127e40a918
3
+ size 718924
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f353ef49a5c69cb68978+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8245d348b9f7b739eaeda2a864dde929542c01a2838309793a437721a049452
3
+ size 19835904