Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/1e9f0775c1252f78667f.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": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.0.dev3",
+    "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-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c3bbd7fc867b9903f6cb1bb028ef67eaea33732fc7afde7b4124bb04d5a50d
+oid sha256:7bbae6ea55f96194c8df2527f71658773b9e0a5a3865d5a0c015c563253f4f77
 size 1434624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5062513634c02e3976177b97dbfe83030caca965f6d94efff0074585baa8c022
+oid sha256:5ca21b014afce4f1adcdca904442c78b7e8e10ec881dd59c586252154a3e9eb4
 size 1521594

neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f8f2bb409247485b54f+408096d6/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63314ff7255f981bbd68fc19cedbbbd15afdc387680049b8d97f3c03edd4bcd
+oid sha256:86996e4861828a06734fa5f01aeadf1d8f16f0aac6ca52fab4e6a2e811668446
 size 2683904

neuronxcc-2.19.8089.0+8ab9f450/MODULE_cdb1257943a078485626+84f3e719/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c81b3204ab5b0f437eb9ffb073d99229c72ec5f7e4185a891bfdc8e767b285c
+oid sha256:3f70c063fae1e0c2e81281eac1bc72a19603b6bdb43eb754c498ef81eb53b3fc
 size 31867904