Synchronizing local compiler cache of TensorVizion/LLaMaPaca

.gitattributes

@@ -17565,3 +17565,6 @@ neuronxcc-2.24.5133.0+58f8de22/MODULE_5983480387230594376+bad9cf09/model.neff fi
 neuronxcc-2.24.5133.0+58f8de22/MODULE_7343260162999572602+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.24.5133.0+58f8de22/MODULE_7903529212460185893+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.24.5133.0+58f8de22/MODULE_8173596499745875930+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_bdd2e93521e55bc08a8f+cb7c900e/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/llama/TensorVizion/LLaMaPaca/16e92d12e1b9f40d8a88.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "TensorVizion/LLaMaPaca",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "TensorVizion/LLaMaPaca",
+    "checkpoint_revision": "09c5e35fdec2f6d3a69a1b5d99b563860c8b9de6",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 4,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "inf2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 4
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.6.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/compile_flags.json

@@ -0,0 +1 @@
+["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54483757e9682d27d0a229b49ec6a1e5241f52868f50afe7012958ee7440ff6
+size 419829

neuronxcc-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495a256110683d70919c71199ffb05ebb39f88dddde1a3c46ad929329802799a
+size 2120704

neuronxcc-2.21.18209.0+043b1bf7/MODULE_580ee573ada99486e248+dfb30fc8/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85e033ea1139d6304cfbd8bfc05e540f275067718963163654c5e330500ab2b
+size 2194812

neuronxcc-2.21.18209.0+043b1bf7/MODULE_bdd2e93521e55bc08a8f+cb7c900e/compile_flags.json

@@ -0,0 +1 @@
+["--target=inf2", "--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/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_bdd2e93521e55bc08a8f+cb7c900e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4956ece64371e0821b617d6b788daa800e68346ec8dd437880eecffd468ad8
+size 510707

neuronxcc-2.21.18209.0+043b1bf7/MODULE_bdd2e93521e55bc08a8f+cb7c900e/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c043544bbd45609b8f30dfc593a3cc0f8b24864d1f0f4c86b0032e131e271b24
+size 21761024