Synchronizing local compiler cache.

.gitattributes

@@ -3249,3 +3249,6 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_d84f59502564753faaf1+431f5505/model.neff fi
 neuronxcc-2.18.121.0+9e31e41a/MODULE_6ec54d1cb60ff01fc2a1+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_6ec54d1cb60ff01fc2a1+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_ef8771b8447d48519ae4+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_1bce819dd943e86ebacb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen3/Qwen/Qwen3-1.7B/13d06bca73e467120958.json

@@ -0,0 +1,72 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-1.7B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "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/Qwen3-1.7B",
+    "checkpoint_revision": "0060bc56d46589041c1048efd1a397421b1142b5",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "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": "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": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.18.121.0+9e31e41a/MODULE_1bce819dd943e86ebacb+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_1bce819dd943e86ebacb+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd240cc4a05841d65b1048379c1685964791ed5c532c39eb202a9d41acc13f4
+size 131996

neuronxcc-2.18.121.0+9e31e41a/MODULE_1bce819dd943e86ebacb+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b733162f6fceed779f646848a2409667a91c228c40dd66191966af66db33a9e2
+size 1281024

neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+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_3596a0566dd0e4bfadf9+5be477de/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5d4146faa890b92be21e8d89202498233a162ed015a12e7b14862f458be4f9
+size 694657

neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d47dfbd1631831caee2e2793e7d785c68cd1fc4f3fa15361729721be0a04156
+size 3533824

neuronxcc-2.18.121.0+9e31e41a/MODULE_3596a0566dd0e4bfadf9+5be477de/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f3ce053f32b2c78555227ee5b6368d60e1d1372e6d2a27868b40cb54a8765b
+size 3663806

neuronxcc-2.18.121.0+9e31e41a/MODULE_6eed81733d4e8aaab34a+84f3e719/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ce125915997a34aa3c0bdd0d160ef2e7dca2fffdd687606acf8d6231fdb047
+oid sha256:49d33b2784e0cd4a06d51a7a9a7d67bbcd022bf78b5e2550b7d77d07f1cde888
 size 829100

neuronxcc-2.18.121.0+9e31e41a/MODULE_6eed81733d4e8aaab34a+84f3e719/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efe0f8e88482b73529155651c4b4d6ac301b10019b33a3b8b48c9ae90b400f7
+oid sha256:7fe4954fa411181d048e90eeec111bbac1ca7ac24ed313c925fd32c717f9aa42
 size 37612544