Synchronizing local compiler cache.

.gitattributes

@@ -10960,3 +10960,6 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_dd67c7d76a4a3b7bc5ff+253d6470/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_26daa9a67a7b665fb215+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed5d870b9654f58c5b37+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed5d870b9654f58c5b37+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_2710681cad85524a4bde+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/qwen3_moe/Qwen/Qwen3-30B-A3B-Instruct-2507/58648c88ee215f4e7231.json

@@ -0,0 +1,66 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+    "checkpoint_revision": "61082d4deaa4785f64943b443cbc2b5de7524fad",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 8,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.1.dev6",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 8
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2158c5d241db88a9d2a27a3c0d18efb20ea416d95f53528d135a760d0c2f3ca0
+size 2502798

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09aa63b61001c4c8bdc215db650979fedab70dbf9ba2a1bfb48c3c95f114c7a7
+size 4066304

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a5e4a426437ae928ea0+cd3419b6/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e9275e544d5e8718773f8926b3e9e9f87b1c8f14d5c911b60ef05f1054881d
+size 4317766

neuronxcc-2.19.8089.0+8ab9f450/MODULE_2710681cad85524a4bde+253d6470/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_2710681cad85524a4bde+253d6470/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f75c0fadf22d53d087da65aceef682754bceff6a392f01be4fad46555a222a
+size 9665709

neuronxcc-2.19.8089.0+8ab9f450/MODULE_2710681cad85524a4bde+253d6470/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf530675200f853e6ed30f5167ccee315d8dbda89d442b0a4ee4173864c7c47b
+size 20112384