Skip to content

Shanmugamr1992/megatron inference ultra#3784

Queued
shanmugamr1992 wants to merge 57 commits intoNVIDIA:mainfrom
shanmugamr1992:shanmugamr1992/megatron_inference_ultra
Queued

Shanmugamr1992/megatron inference ultra#3784
shanmugamr1992 wants to merge 57 commits intoNVIDIA:mainfrom
shanmugamr1992:shanmugamr1992/megatron_inference_ultra

Conversation

@shanmugamr1992
Copy link
Contributor

What does this PR do ?

⚠️ For major changes (either in lines of code or in its impact), please make sure to first share a design doc with the team. If you're unsure what's the best way to do so, contact the @mcore-oncall.

Contribution process

Pre-checks

  • I have added relevant unit tests
  • I have added relevant functional tests
  • I have added proper typing to my code Typing guidelines
  • I have added relevant documentation
  • I have run the autoformatter.sh on my PR

Code review

Feel free to message or comment the @mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!

All PRs start as draft. If you open a non-draft PR, it will be automatically converted to draft.

Step 1: Mark PR as "Ready for Review"

  1. When your PR is ready, click Ready for Review.
  2. An oncall reviewer is auto-assigned and expert reviewers are notified based on your changes.
    • Some PRs may jump straight to step 2. This is determined by .github/CODEOWNERS.

⚠️ Only mark as ready once merge-conflicts are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

Step 2: Final Review

For PRs that change megatron/core, once all expert reviewers have approved, the Final Review label is applied automatically and final reviewers are assigned.

For PRs outside megatron/core, this step is skipped.

Step 3: Approved

Once all required reviewers have approved, the Approved label is applied automatically.

Merge

Any member of mcore-engineers will be able to merge your PR.

For MRs into `dev` branch The proposed review process for `dev` branch is under active discussion.

MRs are mergable after one approval by either eharper@nvidia.com or zijiey@nvidia.com.

@shanmugamr1992 shanmugamr1992 requested review from a team as code owners March 10, 2026 20:17
@copy-pr-bot
Copy link

copy-pr-bot bot commented Mar 10, 2026

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.

@svcnvidia-nemo-ci svcnvidia-nemo-ci marked this pull request as draft March 10, 2026 20:17
@github-actions
Copy link
Contributor

This PR has been automatically converted to draft because all PRs must start as drafts.

When you are ready for review, click Ready for Review to begin the review process. This will:

  1. Add the oncall reviewer (optional reviewer)
  2. Add required review teams based on your changes

See the contribution guide for more details.

@shanmugamr1992 shanmugamr1992 marked this pull request as ready for review March 10, 2026 20:18
@svcnvidia-nemo-ci svcnvidia-nemo-ci requested a review from a team March 10, 2026 20:19
@shanmugamr1992
Copy link
Contributor Author

/ok to test f71f013

@svcnvidia-nemo-ci svcnvidia-nemo-ci added this to the Core 0.16 milestone Mar 10, 2026
Copy link
Contributor

@wdykas wdykas left a comment

Choose a reason for hiding this comment

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

thanks for the annotation for helping refit.


choices.append(choice_data)
if choice_data["generation_log_probs"] is None:
print(f"Generation log probs is None for request:\n{json.dumps(result, indent=4)}", flush=True)
Copy link
Contributor

Choose a reason for hiding this comment

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

Can we put this in a logging statement? Also does this indicate a bug?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done. Put this to loging

Comment on lines +447 to +448
# 'logprobs' in chat API is an object containing 'content'
# "logprobs": {"content": logprobs_content} if logprobs_content else None,
Copy link
Contributor

Choose a reason for hiding this comment

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

Can you remove these lines?

Comment on lines +273 to +274
assert "prompt_token_ids" in last_assistant_message and "generation_token_ids" in last_assistant_message, \
"Last assistant message must have prompt_token_ids and generation_token_ids from previous generation to avoid prefix retokenization"
Copy link
Contributor

Choose a reason for hiding this comment

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

Nit: Can you split this into multiple lines?

@svcnvidia-nemo-ci svcnvidia-nemo-ci added the Final Review PR is in the "final review" stage label Mar 11, 2026
@svcnvidia-nemo-ci svcnvidia-nemo-ci added Approved All necessary approvals have been made and removed Final Review PR is in the "final review" stage labels Mar 11, 2026
@maanug-nv
Copy link
Contributor

/ok to test d43aeca

@shanmugamr1992 shanmugamr1992 added this pull request to the merge queue Mar 11, 2026
@svcnvidia-nemo-ci
Copy link

🔄 Merge queue validation started!

You can track the progress here: https://github.com/NVIDIA/Megatron-LM/actions/runs/22979974974

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Approved All necessary approvals have been made complexity: medium

Projects

None yet

Development

Successfully merging this pull request may close these issues.

10 participants