Skip to content

[Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.compile #18101

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

Jump to bottom
Merged
merged 4 commits into from
May 14, 2025
Merged

[Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.compile #18101

merged 4 commits into from
May 14, 2025

Conversation

pavanimajety
Copy link
Contributor

@pavanimajety pavanimajety commented May 13, 2025 •
edited by github-actions bot
Loading

This is a simple fix to wrap ModelWeightParameter class object back to Parameter class for making it torch.compile compatible.

cc/for review: @LucasWilkinson @mgoin

@pavanimajety
Fix Parameter loading for NVFP4 Linear & MoE Layers for torch.compile
66d519b 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
@pavanimajety
Fix lint
4d669d3 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
@pavanimajety
Make it less verbose
816e90e 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
@github-actions GitHub Actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

LucasWilkinson
LucasWilkinson approved these changes May 13, 2025
View reviewed changes
Copy link
Collaborator

@LucasWilkinson LucasWilkinson left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks! left a couple of non-critical nits

@LucasWilkinson LucasWilkinson enabled auto-merge (squash) May 13, 2025 21:17
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label May 13, 2025
@mgoin mgoin added the bug Something isn't working label May 13, 2025
@pavanimajety
Introduce an env variable to configure MAX_TOKENS_PER_EXPERT
4dafaa1 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
auto-merge was automatically disabled May 13, 2025 22:03

Head branch was pushed to by a user without write access

@pavanimajety
Copy link
Contributor Author

I made another small change and addressed the feedback. Could you take an other look and set the auto-merge again if it looks good? @LucasWilkinson
Thanks!

@vllm-bot vllm-bot merged commit 65f0f74 into vllm-project:main May 14, 2025
64 of 66 checks passed
zzzyq pushed a commit to zzzyq/vllm that referenced this pull request May 24, 2025
@pavanimajety
[Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.c…
4a139ec 
…ompile (vllm-project#18101)

Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Signed-off-by: Yuqi Zhang <yuqizhang@google.com>
minpeter pushed a commit to minpeter/vllm that referenced this pull request Jun 24, 2025
@pavanimajety @minpeter
[Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.c…
64dd3b5 
…ompile (vllm-project#18101)

Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Signed-off-by: minpeter <kali2005611@gmail.com>
@tanujtiwari1998 tanujtiwari1998 mentioned this pull request Jul 8, 2025
Merged
4 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@LucasWilkinson LucasWilkinson LucasWilkinson approved these changes

@DarkLight1337 DarkLight1337 DarkLight1337 left review comments

@mgoin mgoin mgoin approved these changes

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat robertgshaw2-redhat is a code owner

@tlrmchlsmth tlrmchlsmth Awaiting requested review from tlrmchlsmth tlrmchlsmth is a code owner

Assignees
No one assigned
Labels
bug Something isn't working ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@pavanimajety @mgoin @LucasWilkinson @DarkLight1337 @vllm-bot