Skip to content

Conversation

@lmcafee-nvidia
Copy link
Contributor

What does this PR do ?

Revert a recent name change. This PR switches --inference-dynamic-batching-active-buffer-size-gb back to --inference-dynamic-batching-buffer-size-gb. Now, the total buffer size additionally depends on the setting of --inference-dynamic-batching-unified-memory-level:

  • uvm level 0: total buffer size == buffer_size_gb
  • uvm level 1: total buffer size == 2 * buffer_size gb

⚠️ For major changes (either in lines of code or in its impact), please make sure to first share discuss a design-doc with the team.

Contribution process

flowchart LR
    A[Pre-checks] --> B[PR Tests]
    subgraph Code Review/Approval
        C1[Expert Review] --> C2[Final Review]
    end
    B --> C1
    C2 --> D[Merge]
Loading

Pre-checks

  • I want this PR in a versioned release and have added the appropriate Milestone (e.g., Core 0.8)
  • 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

The following process is enforced via the CODEOWNERS file for changes into megatron/core. For changes outside of megatron/core, it is up to the PR author whether or not to tag the Final Reviewer team.

For MRs into `main` branch

(Step 1): Add PR label Expert Review

(Step 2): Collect the expert reviewers reviews

  1. Attach the Expert Review label when your PR is ready for review.
  2. GitHub auto-assigns expert reviewers based on your changes. They will get notified and pick up your PR soon.

⚠️ Only proceed to the next step once all reviewers have approved, merge-conflict are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

(Step 3): Final Review

  1. Add Final Review label
  2. GitHub auto-assigns final reviewers based on your changes. They will get notified and pick up your PR soon.

(Optional Step 4): Cherry-pick into release branch

If this PR also needs to be merged into core_r* release branches, after this PR has been merged, select Cherry-pick to open a new PR into the release branch.

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

MRs are mergable after one approval by either [email protected] or [email protected].

Merging your PR

Any member of core-adlr and core-nemo will be able to merge your PR.

@lmcafee-nvidia lmcafee-nvidia added this to the Core 0.15 milestone Nov 14, 2025
@lmcafee-nvidia lmcafee-nvidia self-assigned this Nov 14, 2025
@lmcafee-nvidia lmcafee-nvidia requested review from a team as code owners November 14, 2025 17:37
@lmcafee-nvidia lmcafee-nvidia added the Expert Review Apply this label to indicate that your PR is ready for expert review. label Nov 14, 2025
@lmcafee-nvidia lmcafee-nvidia requested review from kanz-nv, sidsingh-nvidia and tdene and removed request for sidsingh-nvidia November 14, 2025 17:38
@lmcafee-nvidia lmcafee-nvidia added this pull request to the merge queue Nov 19, 2025
Merged via the queue into NVIDIA:main with commit 21968ea Nov 19, 2025
45 checks passed
@lmcafee-nvidia lmcafee-nvidia deleted the lmcafee/revert-active-buffer-size-name branch November 19, 2025 20:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Expert Review Apply this label to indicate that your PR is ready for expert review.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants