Synchronizing local compiler cache.

.gitattributes

@@ -5317,3 +5317,7 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_nef
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/25991d38bce4cea01a35.json

@@ -0,0 +1,63 @@
+{
+  "_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",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 4,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 5,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "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,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707a314b3cb8d0b9cca6236324024a7ae621644e0b34692f767dc40fd9dcf50e
+size 415281

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2df672ed6f34df0686c1bfbba9d6a2d179520c768482c6ba46254c541e7526
+size 2601984

neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2908d815ecdf47c411fb65abab1f8c0c89a907146ca5585c50e8adf2f4a0c85e
+size 453074

neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330b3501f67ff9b8114338982fe11ddec1492285947061c3cacec10590154531
+size 18975744

neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba77bfe1a58678015961b0cc297841494243fe73291e0b07eb8c2dc21dbd60fd
+size 380078

neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207c81533912f192810c241f23e5ea7d4f4c4ccb654ad8dcd145a1f6dce340f6
+size 1618944

neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcf360b6c528e071bf1851948b8195fcecb45caadf27633a71f04cf37b441a9
+size 1713356