Synchronizing local compiler cache.

.gitattributes

@@ -8675,3 +8675,6 @@ neuronxcc-2.17.194.0+d312836f/MODULE_67d90593bae0dcf21f41+bfe5714b/model.neff fi
 neuronxcc-2.17.194.0+d312836f/MODULE_044c0ca1270ebc46459d+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_ffd03108ca55095db622+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_ffd03108ca55095db622+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_695db2da30bab526bb6b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_8c18088118263e7254d0+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_8c18088118263e7254d0+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-72B-Instruct/34b63559454432fe45b3.json

@@ -0,0 +1,70 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-72B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 4,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct",
+    "checkpoint_revision": "495f39366efef23836d0cfae4fbe635880d2be31",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 24,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev2",
+    "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": 24,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.17.194.0+d312836f/MODULE_695db2da30bab526bb6b+431f5505/compile_flags.json

@@ -0,0 +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-2.17.194.0+d312836f/MODULE_695db2da30bab526bb6b+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec1909a3d7b1736294229f196f7a0c51313d3785a1fbb1fd1fbf0870659fe0f
+size 511796

neuronxcc-2.17.194.0+d312836f/MODULE_695db2da30bab526bb6b+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9629d362165b8fd6c8572dd440ab7751e2762ba7abe29f8130b8d77125df526
+size 7855104

neuronxcc-2.17.194.0+d312836f/MODULE_8ad4d0dd4ea9d9c2284a+165e9558/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81f27a1ca717b95ed4a155d2a2553dfdfa650ffe402c2774416f381593026de
+oid sha256:d7e980d94ddbe18041d6e8ffac0bf477ad6446aceb00a52ce144275d48b0e6e2
 size 2054666

neuronxcc-2.17.194.0+d312836f/MODULE_8c18088118263e7254d0+165e9558/compile_flags.json

@@ -0,0 +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_8c18088118263e7254d0+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41f8877882e5591ebc4b335c808d62a84ac105194ae12dc751e95cdc4256dc2
+size 2020101

neuronxcc-2.17.194.0+d312836f/MODULE_8c18088118263e7254d0+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe49827dbde169c53030089845a337e6331528062f5c374d00063c3f715ec577
+size 8264704

neuronxcc-2.17.194.0+d312836f/MODULE_8c18088118263e7254d0+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a09f10f3cfd5f58230a2dbef53d5418fbbba570ebc2db31a7ab6bfb5508e026
+size 8757248