Synchronizing local compiler cache.

.gitattributes

@@ -3908,3 +3908,6 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_e14a323f877d4623a35c+ed72d204/model.neff f
 neuronxcc-2.20.9961.0+0acef03a/MODULE_ea8966499b21f594b8c4+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_ea8966499b21f594b8c4+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_f46e2e5cf002555b0f87+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_60c3b72c86d3104db4ce+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_60c3b72c86d3104db4ce+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_a0d3fe3774976e0076b5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/gpt_oss/tengomucho/tiny-random-gpt-oss/3b23d0111656ec64befc.json

@@ -0,0 +1,79 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "tengomucho/tiny-random-gpt-oss",
+  "_task": "text-generation",
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "gpt_oss",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "tengomucho/tiny-random-gpt-oss",
+    "checkpoint_revision": "2109d1ee033bb4191af6dd950fda542c9c351dc8",
+    "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": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.1.dev0",
+    "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": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 18,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 2,
+  "num_local_experts": 64,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 150000.0,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 201088
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_60c3b72c86d3104db4ce+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_60c3b72c86d3104db4ce+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c62ba5cf1aa3820c8132321c1386c353f6daf54ef690ebcbb311ecf4d77249
+size 47413

neuronxcc-2.19.8089.0+8ab9f450/MODULE_60c3b72c86d3104db4ce+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb645c7f8440e348b443fa13ae0834d0f1b93cb5acf3e7e75b91ac4367db99e
+size 349184

neuronxcc-2.19.8089.0+8ab9f450/MODULE_60c3b72c86d3104db4ce+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064e9d97b67b647ea0db67f976bc9fd43d5ec186ccf2c1fe4d038b3f8b536c9c
+size 357648

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a0d3fe3774976e0076b5+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_a0d3fe3774976e0076b5+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8571f2d98e8bf1533fa44691bf7b4789d3f051adff0299a6adc709e847ba1c54
+size 18093482

neuronxcc-2.19.8089.0+8ab9f450/MODULE_a0d3fe3774976e0076b5+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1eaca9dc01b6c9382038a5b669a830eb375967d3b040528ba74b2b25ac83ac
+size 3011584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab48cf69ac546f0b2412+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_ab48cf69ac546f0b2412+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5c9479a18e9d96956a19f35c00b2e7709621388d4befe25a6144f15416926a
+size 8556