Skip to content

Conversation

@hyukn
Copy link
Collaborator

@hyukn hyukn commented Nov 25, 2025

We find that release/1.1 also has this issue and may have a potential perf drop.

Summary by CodeRabbit

  • Refactor
    • Optimized internal tensor allocation for NVFP4 uint8 operations in attention processing, improving memory layout efficiency.

✏️ Tip: You can customize this high-level summary in your review settings.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

…IDIA#9336)

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
@hyukn hyukn requested review from QiJune, liji-nv and litaotju November 25, 2025 07:46
@hyukn hyukn requested a review from a team as a code owner November 25, 2025 07:47
@hyukn
Copy link
Collaborator Author

hyukn commented Nov 25, 2025

/bot run --disable-fail-fast

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Nov 25, 2025

📝 Walkthrough

Walkthrough

Modified the scaling factors buffer allocation in the NVFP4 uint8 code path of the attention backend. Changed from using a computed 2D shape to directly allocating a flattened 1D tensor with padded dimensions, altering the memory layout strategy.

Changes

Cohort / File(s) Summary
NVFP4 scaling factors buffer allocation
tensorrt_llm/_torch/attention_backend/trtllm.py
Modified create_output function to allocate scaling factors as a flat 1D tensor using computed padded dimensions (padded_row × padded_col) instead of using compute_swizzled_sf_shape() for 2D shape construction

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

  • Review the memory layout implications of changing from 2D shaped allocation to 1D flattened allocation
  • Verify that the padded dimension computation (padded_row, padded_col) correctly replaces the previous compute_swizzled_sf_shape() logic
  • Confirm that downstream code consuming this buffer still functions correctly with the flattened layout

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)
Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. You can run @coderabbitai generate docstrings to improve docstring coverage.
Description check ⚠️ Warning The PR description lacks critical required sections. It only contains a brief statement about the issue but is missing proper sections for Description, Test Coverage, and incomplete PR Checklist details. Fill in the Description section explaining what the issue is and the solution. Document relevant test coverage in the Test Coverage section. Verify and complete the PR Checklist items, especially noting what testing was performed.
✅ Passed checks (1 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies a specific bug fix (mismatched nvfp4 gemm sf shape) with a bug reference and indicates it's a cherry-pick, directly matching the code changes.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — 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. 📝 Description — Summarize the main change in 50–60 words, explaining what was done.
  2. 📓 References — List relevant issues, discussions, documentation, or related PRs.
  3. 📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.
  4. 📊 Contributor Summary — Include a Markdown table showing contributions:
    | Contributor | Lines Added | Lines Removed | Files Changed |
  5. ✔️ Additional Notes — 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.

❤️ Share

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #25691 [ run ] triggered by Bot. Commit: 819eb39

Copy link
Collaborator

@QiJune QiJune left a comment

Choose a reason for hiding this comment

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

LGTM

@tensorrt-cicd
Copy link
Collaborator

PR_Github #25691 [ run ] completed with state SUCCESS. Commit: 819eb39
/LLM/release-1.1/L0_MergeRequest_PR pipeline #527 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
@hyukn
Copy link
Collaborator Author

hyukn commented Nov 26, 2025

/bot skip --comment "Pipeline has already been cleaned and only change the pre-commit configs."

@tensorrt-cicd
Copy link
Collaborator

PR_Github #25816 [ skip ] triggered by Bot. Commit: 287fed2

@hyukn hyukn enabled auto-merge (squash) November 26, 2025 03:37
@tensorrt-cicd
Copy link
Collaborator

PR_Github #25816 [ skip ] completed with state SUCCESS. Commit: 287fed2
Skipping testing for commit 287fed2

@hyukn hyukn merged commit 816e4d7 into NVIDIA:release/1.1 Nov 26, 2025
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants