Synchronizing local compiler cache (#5)

- Synchronizing local compiler cache (4e82784a7e1e4cb74b3b6cd926513f71c396701e)

.gitattributes

@@ -49,3 +49,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_588559b3f14540f4a099+ed72d204/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_96c31587adfc72adc66e+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_a98b5e3212711e551ddc+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_a98b5e3212711e551ddc+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_7911d68d3b50431f598c+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9101ec316d8143ae76f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0/llama/HuggingFaceTB/SmolLM2-1.7B/5c3ffbe7e6698e345b43.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "HuggingFaceTB/SmolLM2-1.7B",
+  "_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": 8192,
+  "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": "HuggingFaceTB/SmolLM2-1.7B",
+    "checkpoint_revision": "effd688a12921b4cc83e3312b6feb579f70f9c71",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 12,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 128,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 128,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 128,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 12,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7911d68d3b50431f598c+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7911d68d3b50431f598c+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e668fd027a4087cac6cdb2a067c88074342ce7b62c5d1e16cf534466f576b18
+size 101458

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7911d68d3b50431f598c+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a966c1242bd925acf217156327f030c3eea5436372577973acff3bb1fff455f
+size 482304

neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3dae4417854668293c351540f2d27fdef6a17ed9357103665670e7ad7f4707
+size 535393

neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69945eaecf07b9de4b7764ad34ee198b00c3beb043ddb06ba2c7850b0668912
+size 769024

neuronxcc-2.19.8089.0+8ab9f450/MODULE_ad7f6cb4dbef52fda93d+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79db1f883cff2ca8db6958b5bf9c73a022d1076677703b7399e0be6712b23a7
+size 871811

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9101ec316d8143ae76f+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9101ec316d8143ae76f+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31ee57cb56931f73b726beb5e78a82c71c313ec43a8b7ab03c567f93ec21f94
+size 497827

neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9101ec316d8143ae76f+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8241a4cd2024a8d17b64c868e583a8767389f3721a2fa3efdc2744c553553f
+size 850944