Synchronizing local compiler cache.

.gitattributes

@@ -8535,3 +8535,6 @@ neuronxcc-2.17.194.0+d312836f/MODULE_52c63c932893843ad7c8+165e9558/model.neff fi
 neuronxcc-2.17.194.0+d312836f/MODULE_52c63c932893843ad7c8+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_b4d716df46fcca49722f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_c25ac7c9079157fd15ac+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_198ac571c7950482d731+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_198ac571c7950482d731+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_4d810656a0d8bb125a30+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-32B-Instruct/6132504bc792f154c158.json

@@ -0,0 +1,70 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-32B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 8,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-32B-Instruct",
+    "checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
+    "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": 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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev1",
+    "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": 40,
+  "num_hidden_layers": 64,
+  "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_198ac571c7950482d731+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_198ac571c7950482d731+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43ba2ce8a15a0ca97a36d51368e677eff0cb602b931213390b46b4893b566ef
+size 1610010

neuronxcc-2.17.194.0+d312836f/MODULE_198ac571c7950482d731+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5fe5d2d037e8220e0a727753e6b921a2a2fcb2c7f55a0b11026c65cba34556
+size 11346944

neuronxcc-2.17.194.0+d312836f/MODULE_198ac571c7950482d731+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d7ffbbe3eae5e1e3846f5486961cc99a889cfaaced502a4f76832c6aadbefc
+size 11742289

neuronxcc-2.17.194.0+d312836f/MODULE_4d810656a0d8bb125a30+bfe5714b/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/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"

neuronxcc-2.17.194.0+d312836f/MODULE_4d810656a0d8bb125a30+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e125bc5a19bd4d03e4af002165b84b4a55a4e1f740d0b435196f15d6e125d7af
+size 1928010

neuronxcc-2.17.194.0+d312836f/MODULE_4d810656a0d8bb125a30+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf411dcb4af77730d004efb2f283950b4365d7587663e961c88339446da2758e
+size 4660224