Skip to content

build: install cudnn-frontend from feat/1.29.0-megatron in fw_final image - #6427

Open
ZhiyuLi-Nvidia wants to merge 3 commits into
NVIDIA-NeMo:r0.7.0from
ZhiyuLi-Nvidia:zhiyul/build-cudnn-fe-megatron-branch
Open

ZhiyuLi-Nvidia wants to merge 3 commits into
NVIDIA-NeMo:r0.7.0from
ZhiyuLi-Nvidia:zhiyul/build-cudnn-fe-megatron-branch

Conversation

@ZhiyuLi-Nvidia

@ZhiyuLi-Nvidia ZhiyuLi-Nvidia commented Oct 12, 2026 •

Copy link
Copy Markdown
Contributor

Summary

  • Add a CUDNN_FRONTEND_GIT_REF build arg to docker/Dockerfile.fw_final, pinned to the tip of NVIDIA/cudnn-frontend branch feat/1.29.0-megatron.
  • The ref is installed over the PyPI wheel after the environment sync, before the base-runtime check. fw_final re-syncs with fw_pyproject.toml (pins nvidia-cudnn-frontend==1.29.0), so an install made earlier in Dockerfile.ci would be replaced.
  • Skipped when the arg is empty or PRESERVE_BASE_RUNTIME=True.
  • Docker-only: no change to pyproject.toml, fw_pyproject.toml or uv.lock. The Bridge CI image (Dockerfile.ci) is unchanged and keeps the locked wheel.

Not yet verified

  • Test image build (draft until done).
  • That the branch's distribution name and version match nvidia-cudnn-frontend 1.29.0 or higher (gdn_utils.py expects at least 1.29.0).
  • That the image has git and build tools for the native build.

Docs and tests

README build-arg table for Dockerfile.fw_final updated. No Python changes, so no unit tests added.

🤖 Generated with Claude Code

@ZhiyuLi-Nvidia ZhiyuLi-Nvidia added the area:build Dependencies, packaging, images, and environment setup label Oct 12, 2026
@copy-pr-bot

copy-pr-bot Bot commented Oct 12, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@ZhiyuLi-Nvidia ZhiyuLi-Nvidia changed the title build: install cudnn-frontend from feat/1.29.0-megatron in CI image build: install cudnn-frontend from feat/1.29.0-megatron in fw_final image Oct 13, 2026
@cuichenx cuichenx added the ci CI, automation, test queue, or workflow infrastructure work label Oct 13, 2026
balasaajay
balasaajay previously approved these changes Oct 13, 2026
@balasaajay balasaajay added 26.10 r0.7.0 Auto-cherrypick to release branch. Apply before merge; cherrypick happens after merge. labels Oct 13, 2026
@balasaajay
balasaajay marked this pull request as ready for review October 13, 2026 05:15
@balasaajay
balasaajay requested a review from a team as a code owner October 13, 2026 05:15
@ZhiyuLi-Nvidia
ZhiyuLi-Nvidia changed the base branch from main to r0.7.0 October 13, 2026 05:20
@ZhiyuLi-Nvidia
ZhiyuLi-Nvidia dismissed balasaajay’s stale review October 13, 2026 05:20

The base branch was changed.

cuichenx and others added 3 commits October 12, 2026 22:20
Signed-off-by: Chen Cui <chcui@nvidia.com>
Add CUDNN_FRONTEND_GIT_REF build arg to Dockerfile.ci, pinned to the feat/1.29.0-megatron tip. It is installed over the locked wheel after the final uv sync and skipped when PRESERVE_BASE_RUNTIME=True. Docker-only, outside pyproject.toml and uv.lock.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Signed-off-by: Zhiyu Li <zhiyul@nvidia.com>
…fw_final

fw_final inherits the Bridge image and re-syncs with fw_pyproject.toml, which would replace a git install made earlier. Install the feat/1.29.0-megatron ref after that sync instead, and drop it from Dockerfile.ci so it lives in one place.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Signed-off-by: Zhiyu Li <zhiyul@nvidia.com>
@ZhiyuLi-Nvidia
ZhiyuLi-Nvidia force-pushed the zhiyul/build-cudnn-fe-megatron-branch branch from 9912987 to 23e7a10 Compare October 13, 2026 05:20
@ZhiyuLi-Nvidia

Copy link
Copy Markdown
Contributor Author

/ok to test 23e7a10

@github-actions

Copy link
Copy Markdown
Contributor

Automatic Claude reviews have been retired. To request a pull-request review, post a comment containing:

/review

Add model=claude to use a Claude reviewer (the default is model=codex). mode=light|strict selects the review depth; for example, /review model=claude mode=strict. Comment /review help for all options.

@cuichenx cuichenx added the needs-review PR is ready for code review and waiting on a reviewer label Oct 13, 2026

This branch was successfully deployed

1 active deployment
test — 23e7a10d Deployed Oct 13, 2026 by copy-pr-bot[bot] via cicd-wait-in-queue #22809
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

26.10 area:build Dependencies, packaging, images, and environment setup ci CI, automation, test queue, or workflow infrastructure work needs-review PR is ready for code review and waiting on a reviewer r0.7.0 Auto-cherrypick to release branch. Apply before merge; cherrypick happens after merge.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants