Gahow Wang
445e491123
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>
18 lines
477 B
Bash
Executable File
18 lines
477 B
Bash
Executable File
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"
|