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/v1/determinism/conftest.py

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import pytest
+
+import vllm.model_executor.layers.batch_invariant as batch_invariant
+
+
+@pytest.fixture(autouse=True)
+def enable_batch_invariant_mode(monkeypatch: pytest.MonkeyPatch):
+    """Automatically enable batch invariant kernel overrides for all tests."""
+    monkeypatch.setattr(batch_invariant, "VLLM_BATCH_INVARIANT", True)
+    monkeypatch.setenv("VLLM_BATCH_INVARIANT", "1")