Add vLLM v0.18.1 source tree with KV transfer abort fix

third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:

  vllm/v1/core/sched/scheduler.py:
    Replace fatal assert with graceful skip when KV transfer callback
    arrives for an already-aborted request during PD disaggregated serving.

Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-baseline.yaml

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-flashinfer-mxfp4-bf16.yaml

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_MXFP4_BF16: "1"

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass.yaml

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8_CUTLASS: "1"

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-marlin.yaml

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"
+env:
+  VLLM_MXFP4_USE_MARLIN: "1"

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-baseline.yaml

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: openai/gpt-oss-20b
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN"

third_party/vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-sm100-fi-mxfp4-mxfp8-trtllm.yaml

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: "openai/gpt-oss-20b"
+metric_threshold: 0.568
+reasoning_effort: "low"
+server_args: "--tensor-parallel-size 2"
+env:
+  VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8: "1"

third_party/vllm/tests/evals/gpt_oss/configs/models-b200.txt

@@ -0,0 +1,5 @@
+# B200 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-flashinfer-mxfp4-bf16.yaml
+gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass.yaml
+gpt-oss-20b-sm100-fi-mxfp4-mxfp8-trtllm.yaml

third_party/vllm/tests/evals/gpt_oss/configs/models-gfx942.txt

@@ -0,0 +1,3 @@
+# GFX942 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml

third_party/vllm/tests/evals/gpt_oss/configs/models-gfx950.txt

@@ -0,0 +1,3 @@
+# GFX950 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml

third_party/vllm/tests/evals/gpt_oss/configs/models-h100.txt

@@ -0,0 +1,5 @@
+# H100 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-baseline.yaml
+gpt-oss-20b-flashinfer-mxfp4-bf16.yaml
+gpt-oss-20b-marlin.yaml