Synchronizing local compiler cache of meta-llama/Llama-3.2-1B (#11)

- Synchronizing local compiler cache of meta-llama/Llama-3.2-1B (b244c5253af44f6fb198008b61dd5ce6d253bb38)

.gitattributes

@@ -69,3 +69,6 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_67f268f13d78dbbccbec/model.neuron filter=l
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_a521372e1f6ddff8e709+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_b76ed924291f303a724f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_b76ed924291f303a724f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_168718394e19b8c9c0f3+cb7c900e/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/llama/meta-llama/Llama-3.2-1B/c610307e2a365b8fb76b.json

@@ -0,0 +1,61 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.2-1B",
+  "_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": "meta-llama/Llama-3.2-1B",
+    "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 4,
+    "max_batch_size": 1,
+    "max_context_length": 128,
+    "max_topk": 256,
+    "n_active_tokens": 128,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 128,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "inf2",
+    "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,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/compile_flags.json

@@ -0,0 +1 @@
+["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ed297228627e5b57e1e7448b419935e5c01b7f3fc06546e0eb49bbdcf45800
+size 419258

neuronxcc-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ea4c0c3a9b141ada0175ed2c53de679998269b652416929c6fbed946a59c35
+size 1291264

neuronxcc-2.21.18209.0+043b1bf7/MODULE_067dddd6bf85d1ad865e+dfb30fc8/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f595db22ab2a6fd0ea13e946fd14ad8f44d24ba9bd182bcc1cafa645576a51a9
+size 1365369

neuronxcc-2.21.18209.0+043b1bf7/MODULE_168718394e19b8c9c0f3+cb7c900e/compile_flags.json

@@ -0,0 +1 @@
+["--target=inf2", "--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-2.21.18209.0+043b1bf7/MODULE_168718394e19b8c9c0f3+cb7c900e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28920fadcf675e27724d0a8339d42a400d71491c5d9e19a52e280cc603e7125f
+size 378917

neuronxcc-2.21.18209.0+043b1bf7/MODULE_168718394e19b8c9c0f3+cb7c900e/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f0ba2221ec40c84b73406f16abf9412d230f1295299119e5ec069eccc3b32a
+size 1188864