Skip to content

[NV] Add GB200 MegaMOE throughput curve recipes#1223

Open
alec-flowers wants to merge 2 commits intomainfrom
codex/inferencex-gb200-megamoe-curves
Open

[NV] Add GB200 MegaMOE throughput curve recipes#1223
alec-flowers wants to merge 2 commits intomainfrom
codex/inferencex-gb200-megamoe-curves

Conversation

@alec-flowers
Copy link
Copy Markdown
Collaborator

Summary

  • add the validated GB200 Dynamo vLLM MegaMOE mid-curve recipe at conc=256/512/1024
  • rename/update the validated 2P/1D DEP8 MegaMOE high-throughput recipe at conc=4096
  • remove the old no-MegaMOE max-tpt recipe from the GB200 Dynamo vLLM matrix

Validation

  • python3 utils/matrix_logic/generate_sweep_configs.py full-sweep --config-files .github/configs/nvidia-master.yaml --framework dynamo-vllm --model-prefix dsv4 --runner-type gb200

@github-actions
Copy link
Copy Markdown
Contributor

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

1 similar comment
@github-actions
Copy link
Copy Markdown
Contributor

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

@alec-flowers alec-flowers force-pushed the codex/inferencex-gb200-megamoe-curves branch from ea7a22c to 6d44e60 Compare April 29, 2026 06:22
@alec-flowers alec-flowers force-pushed the codex/inferencex-gb200-megamoe-curves branch from 6d44e60 to 750e6dd Compare April 29, 2026 06:28
Comment thread perf-changelog.yaml Outdated
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

1 participant