Synchronizing local compiler cache.

.gitattributes

@@ -5904,3 +5904,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_f1dce126097f38c8bbe1+24129607/model.neff
 neuronxcc-2.22.12471.0+b4a00d10/MODULE_5274831e83842758b831+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.22.12471.0+b4a00d10/MODULE_a968bbe6dc74ca5087a2+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.22.12471.0+b4a00d10/MODULE_a968bbe6dc74ca5087a2+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.22.12471.0+b4a00d10/MODULE_52ac114efcae1dd03863+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/8d8e8248ce11584e8d50.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,
+  "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": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_topk": 256,
+    "n_active_tokens": 8192,
+    "neuronxcc_version": "2.22.12471.0+b4a00d10",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.4.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 8192,
+    "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-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7d005f9cd1245a6b65779b96129bfeb1c4d71cdc854f218e654d67e392ebee
+size 1733130

neuronxcc-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707a75c503e5f4a3bc4de05d829a435db86683439fe141b64bb08ab0f04929b6
+size 2601984

neuronxcc-2.22.12471.0+b4a00d10/MODULE_1167ac875f15bc907a0e+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b3d014612428a6113178275b5cb03acf6ee7b7fcb2b139095373db5716e0be
+size 2676071

neuronxcc-2.22.12471.0+b4a00d10/MODULE_5274831e83842758b831+519f203d/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76537704781b11b3d496666cae05a28ea0940403996348dd002a2f36cc45ae54
+oid sha256:5df396b699dc54f4e90f1bf7132b6f2bb5dbcc31630cb56c922ffa7badde4416
 size 4219904

neuronxcc-2.22.12471.0+b4a00d10/MODULE_52ac114efcae1dd03863+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.22.12471.0+b4a00d10/MODULE_52ac114efcae1dd03863+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7edd18dede90cf40cc04ff8f19696577de8343f225c9eb8144f9af0cbe9f0eb1
+size 1418509

neuronxcc-2.22.12471.0+b4a00d10/MODULE_52ac114efcae1dd03863+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddc86ae908c4fedff86b2f2bb0c3953935d14005bcab08c672eca3f7a76a376
+size 10650624

neuronxcc-2.22.12471.0+b4a00d10/MODULE_a968bbe6dc74ca5087a2+84337dd9/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586b43d7d2f2030a1608cbb68bf9160687432aa2fa26d4a2f656f0ef1005c7b7
+oid sha256:5c87e8fa425f3a6eee0b67b1dc4657a91a4598686e5b0ad9a1b1b8813f61dc24
 size 3257344

neuronxcc-2.22.12471.0+b4a00d10/MODULE_a968bbe6dc74ca5087a2+84337dd9/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425acfb48f46b6e0b3bb71a5de707dfa9221fb2c90637062fc0d5d34f61fb835
+oid sha256:e41012fda7d4998c101efde3a213f17492ad42975b34fb1dbbbac8b7038f6ffd
 size 3331655