Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/56e3ddea3c58aa2dc37d.json +77 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_1b671aa10a6b974deded+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_808e94dfa80c3fc58a91+bfe5714b/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/wrapped_neff.hlo +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_97808204f35ad0303dd2+431f5505/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_bcb977588ee2056b53ff+431f5505/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_d2d90b1d6419ac6fcc6e+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_fee8ece484e30d7945d3+165e9558/wrapped_neff.hlo +1 -1
.gitattributes
CHANGED
|
@@ -8636,3 +8636,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_4201b42b5c6e20215431+165e9558/model.neff fi
|
|
| 8636 |
neuronxcc-2.17.194.0+d312836f/MODULE_4201b42b5c6e20215431+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8637 |
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8638 |
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 8636 |
neuronxcc-2.17.194.0+d312836f/MODULE_4201b42b5c6e20215431+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8637 |
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8638 |
neuronxcc-2.17.194.0+d312836f/MODULE_964372d56efb35dd07e5+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8639 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8640 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/56e3ddea3c58aa2dc37d.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 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": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 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": 16,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"cc_pipeline_tiling_factor": 2,
|
| 25 |
+
"checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 26 |
+
"checkpoint_revision": "6a6f4aa4197940add57724a7707d069478df56b1",
|
| 27 |
+
"continuous_batching": true,
|
| 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": 16,
|
| 37 |
+
"max_context_length": 4096,
|
| 38 |
+
"max_topk": 256,
|
| 39 |
+
"mlp_kernel_enabled": false,
|
| 40 |
+
"mlp_kernel_fuse_residual_add": false,
|
| 41 |
+
"n_active_tokens": 4096,
|
| 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": 4096,
|
| 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": 32,
|
| 62 |
+
"num_hidden_layers": 32,
|
| 63 |
+
"num_key_value_heads": 8,
|
| 64 |
+
"pretraining_tp": 1,
|
| 65 |
+
"rms_norm_eps": 1e-05,
|
| 66 |
+
"rope_scaling": {
|
| 67 |
+
"factor": 8.0,
|
| 68 |
+
"high_freq_factor": 4.0,
|
| 69 |
+
"low_freq_factor": 1.0,
|
| 70 |
+
"original_max_position_embeddings": 8192,
|
| 71 |
+
"rope_type": "llama3"
|
| 72 |
+
},
|
| 73 |
+
"rope_theta": 500000.0,
|
| 74 |
+
"tie_word_embeddings": false,
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 128256
|
| 77 |
+
}
|
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:
|
| 3 |
size 752119
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ea30a4f290b973e2fe1f94f5e5f8ff78dead7075b7f865915584f4b2c3a7e76
|
| 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:
|
| 3 |
size 8162304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d327cc22e8100a7afb089bfc4214fd9ed39f209bcbb18fe942f2addd4d45f2e7
|
| 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:
|
| 3 |
size 8301056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7b6d8a72f26aba41e99cef17a26d48c37cdfb26be0aec5fa3a02e0eb5ae4675
|
| 3 |
size 8301056
|
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:
|
| 3 |
size 890350
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:326d2354334bdff6f2f033c90988866c0ddf476219345489621d952e393eb9aa
|
| 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:
|
| 3 |
size 7824384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2473218c08606d0d42f4fde45773a022f30a716a947edd19a5f21bc2562df09b
|
| 3 |
size 7824384
|
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/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/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
|
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1eea3be3c42a63c9406c837b479fed559bbab0b15ef71009def462ace9dc9cc
|
| 3 |
+
size 771821
|
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:025ddd072ef48ece6a3db5f9da0692410e926cc59ef9200d59bc06fde627cc17
|
| 3 |
+
size 3800064
|
neuronxcc-2.17.194.0+d312836f/MODULE_95673373c334c5511096+165e9558/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a7754635b230163ffe0e324000649cbfeb69f15bd79b1598d02a31be776ff3
|
| 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:
|
| 3 |
size 771805
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e57dfe01466eb61ee80c4cfa643aecc6894d84d21b53c5438c77ea255ee05886
|
| 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:
|
| 3 |
size 3103744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b72fafa70b33dd7f0a5ceba77f20d05578d7e9be0c1e92b47ef09a3921246ce9
|
| 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:
|
| 3 |
size 3241561
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06780fda06f0026709cbf8c0a1bad85857110d81b5bf8af21cbfc871b926d383
|
| 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:
|
| 3 |
size 6124544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:812b0dae8d318a3d062b157ec6634fa55365adebf606150603649b1ace9facdd
|
| 3 |
size 6124544
|
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:
|
| 3 |
size 2202624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:812de76d366557d52146b8eef6bc214c366ee050f70d1311e5b4ef81c91dce46
|
| 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:
|
| 3 |
size 771805
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e8014739cb7e30d51e03902aa0b5aaadc8016b050a5f3256eabdc0cd455e05
|
| 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:
|
| 3 |
size 2530304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6822098837f347f088bafdcd322ad4321453c2734817499a0088794c118c0176
|
| 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:
|
| 3 |
size 2668121
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b632aae5ea14b7c119e15114d45af234c97428982b03ec7c11690f92056e17d
|
| 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:
|
| 3 |
size 751735
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b27c2a5420859caf8f5cc3faa8489f1369b763eeacbdb6361f95bf301b05196
|
| 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:
|
| 3 |
size 7220224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:797a2ddb38f88eb59a32bc38f8349ada00ca47eb11c3bd0e723b8491bc4d12dc
|
| 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:
|
| 3 |
size 7358976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dc327ffd6fb1e1138b859d9192945451ac09bc5cf069159a587818af635c33f
|
| 3 |
size 7358976
|