Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/qwen2/Qwen/Qwen2.5-0.5B/80a2eb5c65245c5a20a0.json

@@ -0,0 +1 @@
+{"_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": {"all_reduce_dtype": null, "allow_flash_attention": true, "attention_layout": "HSB", "attn_output_transposed": false, "auto_cast_type": "fp16", "backend": "hlo", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "collectives_layout": "HSB", "continuous_batching": true, "fuse_qkv": false, "group_query_attention": "shard-over-heads", "log_softmax_scores": false, "neuronxcc_version": "2.17.194.0+d312836f", "optimum_neuron_version": "0.2.0.dev2", "output_all_logits": false, "sequence_length": 4096, "tp_degree": 2}, "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-2.17.194.0+d312836f/MODULE_2e229618015e416964c5+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d756c3a68892a032a24d66f3e29b9b469d015abbdf8415b1a287a4e753f740a6
+oid sha256:eb5f65237f99520ad915afe5fc6a6d2cfbc4e9f19022f28ad5d48e0957ba8c20
 size 1414144

neuronxcc-2.17.194.0+d312836f/MODULE_b9cbc3c9d2c2ba603243+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3013e634ff40e8945572f44dbf8bac20c77b836605920dc80f22a7685bdfb58c
+oid sha256:5d8685c0b0dc2f189f06718967d12718bf11edcbf3a3624f3d616022ac44c0fc
 size 18433024