Synchronizing local compiler cache.

.gitattributes

@@ -4466,3 +4466,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_44955ffeba208f085992+ca355898/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_44955ffeba208f085992+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_55b96c673cac4fb795e7+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_62278754347ea617f01e+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_61e751d22792a685fb04+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_7ab80dc216fdf22f33a4+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/gpt_oss/openai/gpt-oss-20b/aeb56e54e5187a9140e6.json

@@ -0,0 +1,120 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "openai/gpt-oss-20b",
+  "_task": "text-generation",
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "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": "openai/gpt-oss-20b",
+    "checkpoint_revision": "6cee5e81ee83917806bbde320786a8fb61efebee",
+    "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": 8,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 256,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 256,
+    "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": 256,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 8,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
+    ],
+    "quant_method": "mxfp4"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 201088
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_61e751d22792a685fb04+c2248236/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_61e751d22792a685fb04+c2248236/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd0a3508fdaacd90ae9c940631572f114633c0c7ab0982557d5f0f97e1d61ae
+size 1575838

neuronxcc-2.19.8089.0+8ab9f450/MODULE_61e751d22792a685fb04+c2248236/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3807312f82e61b22afc42d422af9c72a31cf96ca36bbee9c144aba429b01e7a
+size 2458624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e7775dec6ecc8e9a9a1abe34b5f3f250ebea073bc5399346aaa4913a4f3a22
+size 860786

neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35384154967ee15b1b517fb9c11cf9aa4ca5a5e8b8b7f992d4b39a9235fee5f1
+size 5161984

neuronxcc-2.19.8089.0+8ab9f450/MODULE_655a970d712c10190223+ca355898/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a372da4b697389d31e9165e7661aecd01638c0e325390138c1e690624275eb3
+size 5329597

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7ab80dc216fdf22f33a4+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_7ab80dc216fdf22f33a4+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56e2678c06694eca1b38d539ad77e1a31801d1a440d223c5f9bb782c127b172
+size 178015

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7ab80dc216fdf22f33a4+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ff4d7b72cf1bd7f1ac7693efc2273e012ba1ffac21c32bbb05827745051ab4
+size 2376704