Synchronizing local compiler cache.

.gitattributes

@@ -9512,3 +9512,6 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_0848e2081f88f7709b92+ed72d204/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_da855c7d06308ad4845c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_da855c7d06308ad4845c+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_f1100b78421bbcd8a825+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo 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/51e221f9ef816ad3ff4b.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 8,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
+    "checkpoint_revision": "6a6f4aa4197940add57724a7707d069478df56b1",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 8,
+    "logical_nc_config": 1,
+    "max_batch_size": 8,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev5",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 8,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/compile_flags.json

@@ -0,0 +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_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c399006b96346ddc3bbf6fb34b8fa58f83424b5569fa38ed694d74f5f6fffe8e
+size 947655

neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbc1dd3e64bb4f6a00bc022c66d0d94ee9f63c53c7ce14c6398210b61fd68d3
+size 31130624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/compile_flags.json

@@ -0,0 +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_977a8cb77ae104c74f77+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b34eff4b00d98d8803ee93ba359acd0931001e4e791c4c83503ee024c2d261
+size 781030

neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6d5deaa271b7ab28ec280f81564f0a1232b5ef2880e224c8cfdcf41ac2e155
+size 3144704

neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568a5bb90dec1dc6fe93fd30494297ac75353e840b26fc46e262e26dfcf33a4c
+size 3282521

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6724b129b0e15a1e673b51eb5d54aeff8e3144f8454ff38d0d1e9db9b51af9
+oid sha256:81871f5818c5a8384da49c2a75ce03b059c7941ac1db1caf4e06cdf152dcf3c8
 size 2509824

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c525fea5f0439318b60a4000ca1900953b4067372cfa9d227b9cbf68a48be01
+oid sha256:b48c7b70611073238308eefeb5e60494c998f16071b76bcb6c32a3854e6c3a38
 size 2647641