Skip to content

fix(container): make vLLM FlashInfer cubin dirs writable #12770

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bewestphal merged 3 commits into from
Aug 10, 2026
Merged

fix(container): make vLLM FlashInfer cubin dirs writable #12770

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
840dc0e
fix(container): make vLLM FlashInfer cubin dirs writable
bewestphal Aug 6, 2026
3d0ae32
Merge branch 'main' into codex/vllm-flashinfer-cubin-permissions
nv-anants Aug 7, 2026
6237556
Merge branch 'main' into codex/vllm-flashinfer-cubin-permissions
bewestphal Aug 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions container/templates/vllm_runtime.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,14 @@ RUN userdel -r ubuntu > /dev/null 2>&1 || true \
&& mkdir -p /etc/profile.d \
&& echo 'umask 002' > /etc/profile.d/00-umask.sh

# FlashInfer creates package-local cubin symlinks at runtime. Grant group 0
# write access so arbitrary OpenShift UIDs can initialize the cubin cache.
RUN SITE_PACKAGES="$(python3 -c 'import site; print(site.getsitepackages()[0])')" && \
CUBINS_DIR="$SITE_PACKAGES/flashinfer_cubin/cubins" && \
if [ -d "$CUBINS_DIR" ]; then \
find "$CUBINS_DIR" -type d -exec chmod g+rwx {} + ; \
fi
Comment thread
bewestphal marked this conversation as resolved.

{% if device != "cuda" %}
# Copy UCX and NIXL from wheel_builder for CPU/XPU devices
# (CUDA devices use NIXL from upstream vLLM wheels)
Expand Down
Loading