Synchronizing local compiler cache.

.gitattributes

@@ -3677,3 +3677,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8cad8a60097b60afe9bb+431f5505/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e61477d57dfc23ed04f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_d45a62468e9816c897a9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B/e2252420d0e4c111b25f.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-7B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "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/Qwen2.5-7B",
+    "checkpoint_revision": "d149729398750b98c0af14eb82c78cfe92750796",
+    "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": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev5",
+    "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": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/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-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd3e2b465da216e06812d8519c549d2f4d85e75c2444788e739b16dd9ff7476
+size 902833

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3a1def4d4bbb23b557b4+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d49387eb62a527167633c8b7eef0a84409dc680134517c0659cd5e5922ff2c
+size 7506944

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+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-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f889f3afe3e6cd45a6bd17e3ef73dc208c21708fc1dd1ad3a5a3c80d5a1b8f18
+size 201977

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a105e663124eac5d157b+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d13aa2dcb5a47e0636e1b771c0bed7e5393d79b1c3adee5f4e96570e43be2e7
+size 6554624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/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-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed49b3652b4f42ce57d1c568c4c3ec3323477cc0f5a45743b3aa2c5f69ac0f38
+size 740826

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f9636be6419181ac51065f002e831f94d1fddecb8fdb1978c660bbc20ed9ac
+size 7384064

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9f9f8371558255bcb45+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312f3025d6c150205d408ca4e813c23f92ac17c47b9d403c6e8e118e7c670bb9
+size 7578631