TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard

[None][chore] AutoDeploy add multi stream moe pass to default.yaml

Open suyoggupta opened this issue 1 month ago โ€ข 12 comments

Summary by CodeRabbit

Release Notes

  • Chores
    • Added new compile-stage transform configuration option (disabled by default) to expand optimization capabilities while maintaining backward compatibility.

suyoggupta avatar Nov 25 '25 05:11 suyoggupta

/bot run

suyoggupta avatar Nov 25 '25 05:11 suyoggupta

๐Ÿ“ Walkthrough

Walkthrough

A new compile-stage transform named multi_stream_moe is added to the default configuration file with the enabled flag set to false, extending the transform pipeline without affecting current behavior.

Changes

Cohort / File(s) Summary
Configuration Updates
tensorrt_llm/_torch/auto_deploy/config/default.yaml
Adds multi_stream_moe transform entry to the transforms section with stage: compile and enabled: false

Estimated code review effort

๐ŸŽฏ 1 (Trivial) | โฑ๏ธ ~2 minutes

Pre-merge checks and finishing touches

โŒ Failed checks (1 warning)
Check name Status Explanation Resolution
Description check โš ๏ธ Warning PR description lacks substantive content; required sections (Description, Test Coverage) are empty beyond template comments. Complete Description and Test Coverage sections with clear explanations of changes, rationale, and test coverage for the multi_stream_moe transform addition.
โœ… Passed checks (2 passed)
Check name Status Explanation
Title check โœ… Passed The title clearly summarizes the main change: adding a multi_stream_moe transform to the default.yaml configuration file in the AutoDeploy module.
Docstring Coverage โœ… Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
โœจ Finishing touches
  • [ ] ๐Ÿ“ Generate docstrings
๐Ÿงช Generate unit tests (beta)
  • [ ] Create PR with unit tests
  • [ ] Post copyable unit tests in a comment

[!TIP]

๐Ÿ“ Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests โ€” including its content, structure, tone, and formatting.

  • Provide your own instructions using the high_level_summary_instructions setting.
  • Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
  • Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

  1. ๐Ÿ“ Description โ€” Summarize the main change in 50โ€“60 words, explaining what was done.
  2. ๐Ÿ““ References โ€” List relevant issues, discussions, documentation, or related PRs.
  3. ๐Ÿ“ฆ Dependencies & Requirements โ€” Mention any new/updated dependencies, environment variable changes, or configuration updates.
  4. ๐Ÿ“Š Contributor Summary โ€” Include a Markdown table showing contributions: | Contributor | Lines Added | Lines Removed | Files Changed |
  5. โœ”๏ธ Additional Notes โ€” Add any extra reviewer context. Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

โค๏ธ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

coderabbitai[bot] avatar Nov 25 '25 05:11 coderabbitai[bot]

PR_Github #25661 [ run ] triggered by Bot. Commit: 12a217d

tensorrt-cicd avatar Nov 25 '25 05:11 tensorrt-cicd

PR_Github #25661 [ run ] completed with state FAILURE. Commit: 12a217d LLM/main/L0_MergeRequest_PR #19448 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd avatar Nov 25 '25 06:11 tensorrt-cicd

/bot run

suyoggupta avatar Nov 25 '25 06:11 suyoggupta

PR_Github #25669 [ run ] triggered by Bot. Commit: 12a217d

tensorrt-cicd avatar Nov 25 '25 06:11 tensorrt-cicd

/bot run

suyoggupta avatar Nov 25 '25 07:11 suyoggupta

PR_Github #25684 [ run ] triggered by Bot. Commit: e486bb8

tensorrt-cicd avatar Nov 25 '25 07:11 tensorrt-cicd

PR_Github #25669 [ run ] completed with state ABORTED. Commit: 12a217d LLM/main/L0_MergeRequest_PR #19454 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd avatar Nov 25 '25 07:11 tensorrt-cicd

/bot run

suyoggupta avatar Nov 25 '25 07:11 suyoggupta

PR_Github #25693 [ run ] triggered by Bot. Commit: 706dc64

tensorrt-cicd avatar Nov 25 '25 07:11 tensorrt-cicd

PR_Github #25684 [ run ] completed with state ABORTED. Commit: e486bb8 LLM/main/L0_MergeRequest_PR #19467 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd avatar Nov 25 '25 07:11 tensorrt-cicd

PR_Github #25693 [ run ] completed with state SUCCESS. Commit: 706dc64 /LLM/main/L0_MergeRequest_PR pipeline #19475 completed with status: 'FAILURE'

tensorrt-cicd avatar Nov 25 '25 15:11 tensorrt-cicd

/bot run

suyoggupta avatar Nov 25 '25 15:11 suyoggupta

PR_Github #25757 [ run ] triggered by Bot. Commit: 706dc64

tensorrt-cicd avatar Nov 25 '25 15:11 tensorrt-cicd

PR_Github #25757 [ run ] completed with state SUCCESS. Commit: 706dc64 /LLM/main/L0_MergeRequest_PR pipeline #19532 completed with status: 'FAILURE'

tensorrt-cicd avatar Nov 25 '25 17:11 tensorrt-cicd

/bot run

suyoggupta avatar Nov 25 '25 18:11 suyoggupta

PR_Github #25770 [ run ] triggered by Bot. Commit: 9363f43

tensorrt-cicd avatar Nov 25 '25 18:11 tensorrt-cicd

PR_Github #25770 [ run ] completed with state SUCCESS. Commit: 9363f43 /LLM/main/L0_MergeRequest_PR pipeline #19545 completed with status: 'SUCCESS' Pipeline passed with automatic retried tests. Check the rerun report for details.

tensorrt-cicd avatar Nov 25 '25 22:11 tensorrt-cicd