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/requirements/rocm.txt

@@ -0,0 +1,23 @@
+# Common dependencies
+-r common.txt
+
+# The version of gRPC libraries should be consistent with each other
+grpcio==1.78.0
+grpcio-reflection==1.78.0
+
+numba == 0.61.2 # Required for N-gram speculative decoding
+
+# Dependencies for AMD GPUs
+datasets
+peft
+pytest-asyncio
+tensorizer==2.10.1
+packaging>=24.2
+setuptools>=77.0.3,<80.0.0
+setuptools-scm>=8
+runai-model-streamer[s3,gcs,azure]==0.15.7
+conch-triton-kernels==1.2.1
+timm>=1.0.17
+# amd-quark: required for Quark quantization on ROCm 
+# To be consistent with test_quark.py
+amd-quark>=0.8.99