Synchronizing local compiler cache.

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/f92daef82938443934d0.json

@@ -0,0 +1,64 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "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": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.4.dev1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "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,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d00a067a62b1f1860deb777f444b9cb08cb6f877ec885847d64ea73763b0efc
+oid sha256:8f7a47d761c50e5ce0c9150e15d0e9f32726afb1e95a6072553758b37a853663
 size 3073024

neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26442807d050083846013c76054618f0984ad4569d6bc245666e9114a5c0a2cb
+oid sha256:c366c2aa9312137e4985670cf006f130a78f6f383ce45c8c327a270a772b4bf8
 size 3147125

neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18debfa97c09c988925a1aaaa8b9c0f8f4cd2b025cbeb08d7ef3bfc4ec9a865f
+oid sha256:dfa7ee587c6dd7eb719c810d0b3390042fe6e1ba6c8c33b36d4f10a723820f13
 size 509380

neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693b83d4f6771c87b8387a60f6b448121dd1c389524ed32f8e1e427f5e1aaacd
+oid sha256:6fcc51a8a2631ef64a3fc55d99615f28707984ec5d38a3df36fa25006a98fe9a
 size 41585664