dacorvo HF Staff commited on
Commit
5b0c394
·
verified ·
1 Parent(s): 25c68ce

Synchronizing local compiler cache.

Browse files
Files changed (28) hide show
  1. .gitattributes +1 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/meta-llama/Llama-2-13b-hf/1323edd1ad44153954c6.json +71 -0
  3. neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.hlo_module.pb +1 -1
  4. neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.neff +1 -1
  5. neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/wrapped_neff.hlo +1 -1
  6. neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/model.hlo_module.pb +1 -1
  7. neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/model.neff +1 -1
  8. neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/wrapped_neff.hlo +1 -1
  9. neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.hlo_module.pb +1 -1
  10. neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.neff +1 -1
  11. neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.hlo_module.pb +1 -1
  12. neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.neff +1 -1
  13. neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/wrapped_neff.hlo +1 -1
  14. neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.hlo_module.pb +1 -1
  15. neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.neff +1 -1
  16. neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/wrapped_neff.hlo +1 -1
  17. neuronxcc-2.17.194.0+d312836f/MODULE_97808204f35ad0303dd2+431f5505/model.neff +1 -1
  18. neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/compile_flags.json +1 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.done +0 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.hlo_module.pb +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.neff +3 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_bcb977588ee2056b53ff+431f5505/model.neff +1 -1
  23. neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.hlo_module.pb +1 -1
  24. neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.neff +1 -1
  25. neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/wrapped_neff.hlo +1 -1
  26. neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.hlo_module.pb +1 -1
  27. neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.neff +1 -1
  28. neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/wrapped_neff.hlo +1 -1
.gitattributes CHANGED
@@ -8666,3 +8666,4 @@ neuronxcc-2.17.194.0+d312836f/MODULE_db3407d86a12ab794718+bfe5714b/model.neff fi
8666
  neuronxcc-2.17.194.0+d312836f/MODULE_cc83c222497224ede995+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8667
  neuronxcc-2.17.194.0+d312836f/MODULE_cc83c222497224ede995+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8668
  neuronxcc-2.17.194.0+d312836f/MODULE_e3d144313513568a6d1b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
8666
  neuronxcc-2.17.194.0+d312836f/MODULE_cc83c222497224ede995+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
8667
  neuronxcc-2.17.194.0+d312836f/MODULE_cc83c222497224ede995+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8668
  neuronxcc-2.17.194.0+d312836f/MODULE_e3d144313513568a6d1b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
8669
+ neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/meta-llama/Llama-2-13b-hf/1323edd1ad44153954c6.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/Llama-2-13b-hf",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "async_mode": false,
21
+ "attn_kernel_enabled": false,
22
+ "batch_size": 1,
23
+ "capacity_factor": null,
24
+ "cc_pipeline_tiling_factor": 2,
25
+ "checkpoint_id": "meta-llama/Llama-2-13b-hf",
26
+ "checkpoint_revision": "5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1",
27
+ "continuous_batching": false,
28
+ "enable_bucketing": false,
29
+ "ep_degree": 1,
30
+ "flash_decoding_enabled": false,
31
+ "fused_qkv": true,
32
+ "glu_mlp": true,
33
+ "is_chunked_prefill": false,
34
+ "local_ranks_size": 8,
35
+ "logical_nc_config": 1,
36
+ "max_batch_size": 1,
37
+ "max_context_length": 2048,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 2048,
42
+ "neuronxcc_version": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev2",
46
+ "output_logits": false,
47
+ "padding_side": "right",
48
+ "pp_degree": 1,
49
+ "qk_layernorm": false,
50
+ "qkv_kernel_enabled": false,
51
+ "rpl_reduce_dtype": "bfloat16",
52
+ "sequence_length": 2048,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "bfloat16",
58
+ "tp_degree": 8,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 40,
62
+ "num_hidden_layers": 40,
63
+ "num_key_value_heads": 40,
64
+ "pretraining_tp": 1,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": null,
67
+ "rope_theta": 10000.0,
68
+ "tie_word_embeddings": false,
69
+ "use_cache": true,
70
+ "vocab_size": 32000
71
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ea30a4f290b973e2fe1f94f5e5f8ff78dead7075b7f865915584f4b2c3a7e76
3
  size 752119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66dc9dabbc3ee5034c9c9d76c1f6f08db78cc883c88ff6fed1b619adfa9308e2
3
  size 752119
neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d327cc22e8100a7afb089bfc4214fd9ed39f209bcbb18fe942f2addd4d45f2e7
3
  size 8162304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a802b01b58cdd57208baf3da1ded5446cc63429509c52a83ef2c7f561276996
3
  size 8162304
neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7b6d8a72f26aba41e99cef17a26d48c37cdfb26be0aec5fa3a02e0eb5ae4675
3
  size 8301056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6c792d414a3cd46003c750d8ac7d82571df0b7cf4661d8bb8629d53428e19b
3
  size 8301056
neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0617ad7ea61c26ba4e3ef38736179394e71e27edd53a084ee9a3122bc9c7f50b
3
  size 772205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aacaf9581227b1e5b8839963f261469bb28db84e98a7d2fab8fc0b687417865
3
  size 772205
neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95aeb32c1a0e924670b90e199a277c3d70abe9cfd521223c4161b8e44b93dd92
3
  size 4957184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87de262d4e38d2080c9529b825f7767f79ab6cf3b82279f77d90635209bf4c94
3
  size 4957184
neuronxcc-2.17.194.0+d312836f/MODULE_30b7ee7e00d3893e49cf+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e5f4ef2e67c6baba357523b263cb8f3134b795b5536d65a814dbb4876b850e
3
  size 5095001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb31e76a630a68399922fb0fe7faedd8d1776293900f0c975fd5af839505363
3
  size 5095001
neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326d2354334bdff6f2f033c90988866c0ddf476219345489621d952e393eb9aa
3
  size 890350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d13e8b67cf61c4a20ff16a657dab67ffeee573626a8365b7667ce26743137ed
3
  size 890350
neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2473218c08606d0d42f4fde45773a022f30a716a947edd19a5f21bc2562df09b
3
  size 7824384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0c07fd5bf05f5dd8093c7c18f6dfeb7aa7f85d900d5256d793f7365f97bcab
3
  size 7824384
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1eea3be3c42a63c9406c837b479fed559bbab0b15ef71009def462ace9dc9cc
3
  size 771821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f26b2aa02658f1fe7ca996ebcde85589398322587b4bba303d33c7341a94ac
3
  size 771821
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:025ddd072ef48ece6a3db5f9da0692410e926cc59ef9200d59bc06fde627cc17
3
  size 3800064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e813fd0d226aff3a035b95edbf5501c637efff2ee0c35121917f59e880a0326
3
  size 3800064
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1a7754635b230163ffe0e324000649cbfeb69f15bd79b1598d02a31be776ff3
3
  size 3937881
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e44f69d2760f056b9600cefaeb5c85780b6c985c2383e18877e818657e8d53
3
  size 3937881
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e57dfe01466eb61ee80c4cfa643aecc6894d84d21b53c5438c77ea255ee05886
3
  size 771805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bc345a7678b0a4cfdfbc05c32ac8f6aed6e87334bd27467797a5d0d866d4cb
3
  size 771805
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b72fafa70b33dd7f0a5ceba77f20d05578d7e9be0c1e92b47ef09a3921246ce9
3
  size 3103744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddd1b6d9fd57d1d1ae80c5b8e9da609cb9628408c5560426e3b4acf4f22d685
3
  size 3103744
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06780fda06f0026709cbf8c0a1bad85857110d81b5bf8af21cbfc871b926d383
3
  size 3241561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32133396c4309715351ab4bb789773bf2fbbc4ab6b1167c48075d14b54e18519
3
  size 3241561
neuronxcc-2.17.194.0+d312836f/MODULE_97808204f35ad0303dd2+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:812b0dae8d318a3d062b157ec6634fa55365adebf606150603649b1ace9facdd
3
  size 6124544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae34b59090d1e462c27d840613f9a315e67d4e191daa7ade1865ea449b4fa82
3
  size 6124544
neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b260b07dca312f2edb4d2ee926f5055dc103986e58aefadb3b65f3ab72a624f
3
+ size 774478
neuronxcc-2.17.194.0+d312836f/MODULE_ad57db5ffb22fc0e0bfc+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5922b36988c6420733d3fe430ecf4e6f7ef668eb580d6c2c0aea617dc997e35
3
+ size 24771584
neuronxcc-2.17.194.0+d312836f/MODULE_bcb977588ee2056b53ff+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:812de76d366557d52146b8eef6bc214c366ee050f70d1311e5b4ef81c91dce46
3
  size 2202624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc2e5e0f0a6a1efd05101847cb2e5cc346c21d65257adac1f89cead4754a8b9
3
  size 2202624
neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63e8014739cb7e30d51e03902aa0b5aaadc8016b050a5f3256eabdc0cd455e05
3
  size 771805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a465268673618b3da8b5d1c645e0c1f65a449bfd0cdb845f9a6b0f6f49ce960
3
  size 771805
neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6822098837f347f088bafdcd322ad4321453c2734817499a0088794c118c0176
3
  size 2530304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c342f6c3ed02b28ea575f02e2e79d962de5f4a1b2a4218375981ad9c0e15d8
3
  size 2530304
neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b632aae5ea14b7c119e15114d45af234c97428982b03ec7c11690f92056e17d
3
  size 2668121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2110a650ad923da022feee5601ade18b8e4d77ea306408da015a758e521c47
3
  size 2668121
neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b27c2a5420859caf8f5cc3faa8489f1369b763eeacbdb6361f95bf301b05196
3
  size 751735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd192eece819dfb38effa2311baf555a6d48251df2a9d9493a7b6c8495231bb5
3
  size 751735
neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:797a2ddb38f88eb59a32bc38f8349ada00ca47eb11c3bd0e723b8491bc4d12dc
3
  size 7220224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c800c687dd928cc98c2b5b7eb2f85882946bf658669addd6fdcfd438bd7e9c09
3
  size 7220224
neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dc327ffd6fb1e1138b859d9192945451ac09bc5cf069159a587818af635c33f
3
  size 7358976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba0d5bfc347e10b47d938d1fbc325760323d05f985a9587f0dc7f54e3ec19bf
3
  size 7358976