Synchronizing local compiler cache.

.gitattributes

@@ -3239,3 +3239,6 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff fi
 neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_de463290b0cc81f3e50a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/0a7538585ea13b5015c5.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "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/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "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": 2,
+    "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": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "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": "float16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4bb2fd6d46cb6897204c4c8641e2005c70f8ced561f1982a11c71628cc9dd6a
+oid sha256:a4fde40ac8554149e3a7f55fe8544ffe7707f966f4862c07c50b5339c20aa946
 size 703084

neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddeb5472f1aaa043b92459ac583c010976046b17bd5659fcba52cca4f23d9bc
+oid sha256:71c4474f3125676619cebf400e0ed9213dd05978e7bf27d8c4964fbcd273d87e
 size 20030464

neuronxcc-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/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-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-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8a0a7013c110b44aaaec4b50cae1e5959e1913beb3ea2335d8adbb455acfa5
+size 576230

neuronxcc-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b1138ebe3f62088327a2428db224262e929c355536aaf04de91e9d3132b941
+size 1455104

neuronxcc-2.18.121.0+9e31e41a/MODULE_b254587b1ec9eec17e0e+5be477de/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429d088ab1dfb766759c35adfa2f83005597386e8dde5d9d029a3578829812e5
+size 1600015

neuronxcc-2.18.121.0+9e31e41a/MODULE_de463290b0cc81f3e50a+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-2.18.121.0+9e31e41a/MODULE_de463290b0cc81f3e50a+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffa79e252b3ab5a178f15d5680b162a5ff48ece318bf95a4122231f100bd639
+size 149912

neuronxcc-2.18.121.0+9e31e41a/MODULE_de463290b0cc81f3e50a+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34394f78095d1b09e75e68a06fa50102f9fd996fd1e4ca6cbb60bd60faa3c5ee
+size 594944