Add vLLM patches directory for version-controlled patch management

patches/0001-fix-kv-transfer-abort-race.patch:
  Fix scheduler assert crash when KV transfer callback arrives
  after request abort in PD-disaggregated serving.

patches/README.md:
  How to apply patches to source tree or installed package.
  Per-patch description with problem/fix/impact.

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

patches/0001-fix-kv-transfer-abort-race.patch

@@ -0,0 +1,24 @@
+--- a/vllm/v1/core/sched/scheduler.py
++++ b/vllm/v1/core/sched/scheduler.py
+@@ -2097,7 +2097,9 @@
+         # KV Connector:: update recv and send status from last step.
+         for req_id in kv_connector_output.finished_recving or ():
+             logger.debug("Finished recving KV transfer for request %s", req_id)
+-            assert req_id in self.requests
++            if req_id not in self.requests:
++                logger.warning("Skipping finished_recving for unknown request %s (already aborted?)", req_id)
++                continue
+             req = self.requests[req_id]
+             if req.status == RequestStatus.WAITING_FOR_REMOTE_KVS:
+                 self.finished_recving_kv_req_ids.add(req_id)
+@@ -2106,7 +2108,9 @@
+                 self._free_blocks(self.requests[req_id])
+         for req_id in kv_connector_output.finished_sending or ():
+             logger.debug("Finished sending KV transfer for request %s", req_id)
+-            assert req_id in self.requests
++            if req_id not in self.requests:
++                logger.warning("Skipping finished_sending for unknown request %s (already aborted?)", req_id)
++                continue
+             self._free_blocks(self.requests[req_id])
+
+     def _update_requests_with_invalid_blocks(

patches/README.md

@@ -0,0 +1,30 @@
+# vLLM Patches
+
+Patches against vLLM v0.18.1. Apply to either the source tree (`third_party/vllm/`) or the installed package.
+
+## Applying
+
+```bash
+# To source tree (for rebuilding)
+cd third_party/vllm && git apply ../../patches/*.patch
+
+# To installed package (quick, no rebuild)
+SITE=$(python -c "import vllm; print(vllm.__path__[0])")
+for p in patches/*.patch; do
+    patch -p1 -d "$(dirname $SITE)" < "$p"
+done
+```
+
+## Patches
+
+### 0001-fix-kv-transfer-abort-race.patch
+
+**File**: `vllm/v1/core/sched/scheduler.py`
+
+**Problem**: When a client disconnects (timeout/abort) during PD-disaggregated serving, the Mooncake KV transfer callback arrives after the request has been removed from the scheduler. The `assert req_id in self.requests` kills the engine process.
+
+**Fix**: Replace fatal assert with graceful skip + warning log.
+
+**Impact**: Without this patch, decode instances crash after ~200 requests under sustained load with concurrent KV transfers.
+
+**Upstream**: Not yet submitted. Could be upstreamed to vllm-project/vllm.