Synchronizing local compiler cache.

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/unsloth/Llama-3.2-1B-Instruct/4bd335fd3628ad3c627d.json

@@ -0,0 +1,78 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_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",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "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.dev1",
+    "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": 5,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "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-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9728a649e6052172bbb32924709bab6791dc8ddc7e57ddf824887a9c1770f7
+oid sha256:1d127c5e076c9548a414b6613237c89ad0a20015b41104775a2863c1600ce486
 size 1455104

neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3b3fdf77a2d7feb51ba3a86d9d301bdc45a27fff20d68ae18dabaeb0f4efaa
+oid sha256:c462ba3510991b31adfcc6dde9cf54df7940dc8b56fde559da5141a2dd3cc59a
 size 1542074

neuronxcc-2.18.121.0+9e31e41a/MODULE_4f5bfc8fac70e593d4ab+84f3e719/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb91e759a25eaffe73033a3c67c1445e7dcca30d01218861ab205aa55c43ab1
+oid sha256:4a6a3fa030f18b4394c10cc2f9db4235964e04369b36e64ff4741b06db1d71af
 size 31878144

neuronxcc-2.18.121.0+9e31e41a/MODULE_8f8f2bb409247485b54f+408096d6/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5450a7e198948e180b8847b60f922534d64dda37619fc64c5582261d5ba595c3
+oid sha256:4f55a35049aeacc1d387135e109ff1c4224e8697fc1ddb840c99468fe9fcc045
 size 2683904