Synchronizing local compiler cache.

.gitattributes

@@ -7210,3 +7210,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/b5b967f1344568be9f11f63a5204f3922ed120215715eeffa2c5fc0a90998346/986c7fbb3beaa00501ce.json

@@ -0,0 +1,85 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_topk": 256,
+    "n_active_tokens": 8192,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 1024,
+    "sequence_length": 8192,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "original_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba88729e59e28a7023865f1f7aa71f1fbe0921fea68be5f09fe60410d99b0203
+size 901341

neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4e76d92ae1280bc571cf0de942e8b7822bc0adb11745373e7ecdc84b28af55
+size 29604864

neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0153fdbba00313e04519191fbb4dc34a1eb23fe534abab81183e8c07863861
+size 700565

neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125955a823da443c495bd368e75c9fdf9f5bf5ddbd3130282bfdac172e264d48
+size 1977344

neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1f815f57302d606c259061d99ca51a8e0a21ed5fd65a052368d3f5c8b536c5
+size 2135210