Synchronizing local compiler cache.

.gitattributes

@@ -45,3 +45,7 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_42c7c80374d4e8712757/model.neuron filter=lf
 neuronxcc-2.16.372.0+4a9b2326/MODULE_fce72056449004b51385/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_925eeddec3d7c8386722/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_588559b3f14540f4a099+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+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+8ab9f450/0_REGISTRY/0.3.0/llama/HuggingFaceTB/SmolLM2-135M-Instruct/a21dd105632468df5951.json

@@ -0,0 +1,79 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "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/SmolLM2-135M-Instruct",
+    "checkpoint_revision": "a91318be21aeaf0879874faa161dcb40c68847e9",
+    "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": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_588559b3f14540f4a099+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_588559b3f14540f4a099+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a8e8069e7da1420af11e48607d7def1a5bccea2b2be0c7a265b57d3227a9ac
+size 571739

neuronxcc-2.19.8089.0+8ab9f450/MODULE_588559b3f14540f4a099+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bfd3b6e97d007fb90bddd1929e18188da84a189ed9e0af47b46d3f66c5a485
+size 502784

neuronxcc-2.19.8089.0+8ab9f450/MODULE_96c31587adfc72adc66e+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_96c31587adfc72adc66e+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e70d5188007356b8af110db8f51de5f20ddb1a87839dab60ffa32661fe0845
+size 97422

neuronxcc-2.19.8089.0+8ab9f450/MODULE_96c31587adfc72adc66e+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e9f32ee9d9296a7b7fdfa6f0f3622215a466e863771f9bf39f9297c3ea4d94
+size 154624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a98b5e3212711e551ddc+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_a98b5e3212711e551ddc+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738496da0607ce3f98a5c60d167ee4999220aca671bb3e6e8f35ce318f9a061d
+size 617947

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a98b5e3212711e551ddc+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d67acd5a7a163cc53ca491ed987d23c8ab6c890d90da3ea67f9edaa2a9e7994
+size 615424

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a98b5e3212711e551ddc+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac52889c19fadb7ebb93a99e8567fad91204ccb42b7ee210f451576d1a2e1f3
+size 716633