Synchronizing local compiler cache.

.gitattributes

@@ -2786,3 +2786,7 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_4f54951d7f1d19705651+613edded/model.neff fi
 neuronxcc-2.18.121.0+9e31e41a/MODULE_887308291049e2c08d88+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_2db40b5b23a523e16b87+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_967d83f73b8fe30e4d14+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_4f5bfc8fac70e593d4ab+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_8f8f2bb409247485b54f+408096d6/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/unsloth/Llama-3.2-1B-Instruct/5a79ca4dbc69ef71b833.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": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "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-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df80a76638714f7b3ae14090f869998613463e6f5413a1c3706af6f60ad19d62
+size 375531

neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9b259698ffe4ef964d57fb214b111d476fefec8dd0eb0849edf65e71bcdc95
+size 1455104

neuronxcc-2.18.121.0+9e31e41a/MODULE_0b8b4fa5620a4855f332+5be477de/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86fcf10f74cf637cbc442fb76a92fd73f2bd60cdc7925f26c601a238d21e841
+size 1542074

neuronxcc-2.18.121.0+9e31e41a/MODULE_4f5bfc8fac70e593d4ab+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_4f5bfc8fac70e593d4ab+84f3e719/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2383c9d55c2657ab334a06fe7200efa4e3e7756db415d2f60f8d004f28a8684
+size 376942

neuronxcc-2.18.121.0+9e31e41a/MODULE_4f5bfc8fac70e593d4ab+84f3e719/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3032686fea57f8ab575d290b98de9840bc976225d306340379c8b8fc9a179d4e
+size 31878144

neuronxcc-2.18.121.0+9e31e41a/MODULE_8f8f2bb409247485b54f+408096d6/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_8f8f2bb409247485b54f+408096d6/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7e167aa7ccd034fc9c89f5ad9e1b7c70c446c20ff2575df0e2211d8eb5426e
+size 410718

neuronxcc-2.18.121.0+9e31e41a/MODULE_8f8f2bb409247485b54f+408096d6/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb462f664ab055dea20d3cd6f1cd621924952351952c5686a7c2f07cdc5de99e
+size 2683904