Synchronizing local compiler cache.
Browse files- .gitattributes +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/7b16e5ee46b35c291731.json +77 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo +1 -1
.gitattributes
CHANGED
|
@@ -9535,3 +9535,6 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b2c47f076c771f823c6a+a9d440f5/wrapped_neff
|
|
| 9535 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb788a6d46d34fecb5c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9536 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_afe48c34a0ccf86323ee+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9537 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_afe48c34a0ccf86323ee+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 9535 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fb788a6d46d34fecb5c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9536 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_afe48c34a0ccf86323ee+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9537 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_afe48c34a0ccf86323ee+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9538 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9539 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9540 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/7b16e5ee46b35c291731.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": 32,
|
| 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": 32,
|
| 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": "2.19.8089.0+8ab9f450",
|
| 43 |
+
"num_cores_per_group": 1,
|
| 44 |
+
"on_device_sampling": true,
|
| 45 |
+
"optimum_neuron_version": "0.3.0.dev5",
|
| 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-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 947655
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c399006b96346ddc3bbf6fb34b8fa58f83424b5569fa38ed694d74f5f6fffe8e
|
| 3 |
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31130624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcbc1dd3e64bb4f6a00bc022c66d0d94ee9f63c53c7ce14c6398210b61fd68d3
|
| 3 |
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+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_40c6949869ebcdeedaf2+a9d440f5/model.done
ADDED
|
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51b804c3554b0472186eb02163bce8904cd8056f34b72ec341ba6b6d16ad52c8
|
| 3 |
+
size 781430
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fb0070af584295dd6285c8a81c9e2a23a2228afcd40aecb54cabf763d4a08b8
|
| 3 |
+
size 4946944
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:980b08a3d585a5028932197799031d54a4f422dcad80fb0f422fa2e8a75f057e
|
| 3 |
+
size 5084761
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 947655
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:344c4bc4f621e87f2aa6a2bbfaf4a6e25ec60f43ada7685289202fa2727383bf
|
| 3 |
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31130624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d07c5df094dc0a3a2f756a022d4628e79090744a074901ef727ee1dd413e30f9
|
| 3 |
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3144704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a6d5deaa271b7ab28ec280f81564f0a1232b5ef2880e224c8cfdcf41ac2e155
|
| 3 |
size 3144704
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3282521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:568a5bb90dec1dc6fe93fd30494297ac75353e840b26fc46e262e26dfcf33a4c
|
| 3 |
size 3282521
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2509824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81871f5818c5a8384da49c2a75ce03b059c7941ac1db1caf4e06cdf152dcf3c8
|
| 3 |
size 2509824
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2647641
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b48c7b70611073238308eefeb5e60494c998f16071b76bcb6c32a3854e6c3a38
|
| 3 |
size 2647641
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+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_a05cd854c08da3538898+ed72d204/model.done
ADDED
|
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:052268bdd18341b626c017384e77add1212fc423ce025e12d4ba52e4426ff00b
|
| 3 |
+
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d3732617b0128dd5398936a00cf986a8857e28585f52cb932db04df48ef57b
|
| 3 |
+
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3871744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6455505999f318298bd9c922db8446eb2945a0c2fcd7078851ee360653259b2
|
| 3 |
size 3871744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4009561
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:940b761e425c43626c45170ed60dc175957d65c900eac43c9cbd5404d3c52fe3
|
| 3 |
size 4009561
|