Synchronizing local compiler cache.

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/1acefa4e5f511f842621.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.dev3",
+    "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:a4fde40ac8554149e3a7f55fe8544ffe7707f966f4862c07c50b5339c20aa946
+oid sha256:e5a7528049b36cdbed8306f77a805f7975e14989abaa3b149a81d2e9ba494b45
 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 sha256:71c4474f3125676619cebf400e0ed9213dd05978e7bf27d8c4964fbcd273d87e
+oid sha256:1feff0680d34a7a7ecb1e12e224631b507c87115647a2f4b3f12706822df324f
 size 20030464

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b1138ebe3f62088327a2428db224262e929c355536aaf04de91e9d3132b941
+oid sha256:2413003a4e0a0fcac5893e5ac571f5dfd433be3302ac2cff1efe5609a8a5c65e
 size 1455104

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429d088ab1dfb766759c35adfa2f83005597386e8dde5d9d029a3578829812e5
+oid sha256:0ee896ee9eca43cf16b4a92a30cf45f0d33bdad46ea6762a1bab213aa6bdf3e8
 size 1600015

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34394f78095d1b09e75e68a06fa50102f9fd996fd1e4ca6cbb60bd60faa3c5ee
+oid sha256:80c322716d2c85c3db89f340838f02b6b182a3cbb1484ddbc51850e54a437777
 size 594944