Synchronizing local compiler cache.

.gitattributes

@@ -7219,3 +7219,7 @@ neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_nef
 neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b1cbe55c91f993ef982f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_c767c3f27ea0e698f8a2+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/36bddeeb8fa0112ceb9a30beea2e66ccfb0badbd70fb11e109649843f84a4b4f/c51466a58158a0826872.json

@@ -0,0 +1,65 @@
+{
+  "_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": 128,
+  "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,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 4096,
+    "speculation_length": 5,
+    "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,
+  "original_head_dim": 64,
+  "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_b1cbe55c91f993ef982f+24129607/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--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-2.21.33363.0+82129205/MODULE_b1cbe55c91f993ef982f+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f244af582e34500d34de87cca7ab0390ba4cdf324f6b98ebfe618071e355a169
+size 414188

neuronxcc-2.21.33363.0+82129205/MODULE_b1cbe55c91f993ef982f+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcb24ffbc256959741e164a6bdd195cda0134b2c95a469d0ef29b938a39f615
+size 44401664

neuronxcc-2.21.33363.0+82129205/MODULE_c767c3f27ea0e698f8a2+677eeb9d/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--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/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_c767c3f27ea0e698f8a2+677eeb9d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7baa8c0ccf70593d5f401ec9293ce64ab65295cbf4c83537026395514d239dae
+size 476295

neuronxcc-2.21.33363.0+82129205/MODULE_c767c3f27ea0e698f8a2+677eeb9d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee77f6b5fa044fe76a01d66dff6044fef24fb8e4a6e1fb1ff14b36fd959ddb5
+size 3974144

neuronxcc-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--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-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0915a3e268fdcbd3a6afa0f512490384b20af67d7a3e353bfcab462596fa1391
+size 426168

neuronxcc-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f867563efca26dffddd4efa75227bb4f8589fa050036d145134614dfb6e18fc
+size 1987584

neuronxcc-2.21.33363.0+82129205/MODULE_d07f3a4497e25890add6+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd9ddfdaa6cbd4b842711c926182ac26778089b2df0ef930e95eb341f263ebe
+size 2081345