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/tools/ep_kernels/configure_system_drivers.sh

@@ -0,0 +1,17 @@
+set -ex
+
+# turn on IBGDA
+echo 'options nvidia NVreg_EnableStreamMemOPs=1 NVreg_RegistryDwords="PeerMappingOverride=1;"' | tee -a /etc/modprobe.d/nvidia.conf
+
+if command -v update-initramfs &> /dev/null; then
+    # for Debian/Ubuntu
+    sudo update-initramfs -u
+elif command -v dracut &> /dev/null; then
+    # for Fedora/CentOS
+    sudo dracut --force
+else
+    echo "No supported initramfs update tool found."
+    exit 1
+fi
+
+echo "Please reboot the system to apply the changes"