Skip to content

Comments

[None][doc] Adding parallelism types in feature combination matrix#9849

Merged
pcastonguay merged 6 commits intoNVIDIA:mainfrom
pcastonguay:update_feat_combination_matrix
Jan 7, 2026
Merged

[None][doc] Adding parallelism types in feature combination matrix#9849
pcastonguay merged 6 commits intoNVIDIA:mainfrom
pcastonguay:update_feat_combination_matrix

Conversation

@pcastonguay
Copy link
Collaborator

@pcastonguay pcastonguay commented Dec 9, 2025

Summary by CodeRabbit

  • Documentation
    • Expanded the feature combination matrix with additional parallelism options (Tensor, Pipeline, and Expert Parallelism).
    • Reorganized the matrix structure and added status indicators for untested feature combinations to improve clarity and maintainability.

✏️ 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.

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
@pcastonguay pcastonguay requested a review from a team as a code owner December 9, 2025 18:56
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Dec 9, 2025

📝 Walkthrough

Walkthrough

The feature compatibility matrix documentation was restructured to include additional parallelism columns: Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism. Rows were reordered with corresponding cell values updated to align with the new column layout, and untested statuses were marked appropriately.

Changes

Cohort / File(s) Summary
Documentation Table Restructuring
docs/source/features/feature-combination-matrix.md
Expanded 2D matrix with three new columns (Tensor Parallelism, Pipeline Parallelism, Expert Parallelism); reordered rows and updated header/separator formatting; marked untested entries; maintained semantic relationships.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description is entirely empty—only the template structure is present with all content sections unfilled (no title provided, Description blank, Test Coverage blank, and only boilerplate checklist text). Fill in the PR description with a proper title following [type] format, explain what changes were made and why, document relevant test coverage, and complete the PR checklist items appropriately.
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly describes the main change—adding parallelism types to the feature combination matrix documentation.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

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.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (1)
docs/source/features/feature-combination-matrix.md (1)

3-22: Consider adding a note to clarify the lower-triangular matrix design.

The matrix is structured as a lower-triangular table where only features at index i are tested for compatibility with features at indices j < i (plus self-compatibility on the diagonal). The upper triangle is intentionally left empty. While this is a valid design choice for space efficiency, readers may find it unclear without an explicit note explaining this structure.

Example note to add before the table:

Note: This matrix shows feature compatibility relationships. Each row displays how that feature works with all previously listed features (and itself on the diagonal). The diagonal shows "---" for self-compatibility. Compatibility is marked as "Yes", "No", or "Untested".
📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 07c76a5 and 24b6ee6.

📒 Files selected for processing (1)
  • docs/source/features/feature-combination-matrix.md (1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: Pre-commit Check
🔇 Additional comments (1)
docs/source/features/feature-combination-matrix.md (1)

3-22: Verify that cell values were correctly migrated when restructuring the matrix.

The PR restructures the feature matrix to add Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism as new columns. Since all lines are marked as changed, it's difficult to assess whether each cell was properly updated during this reorganization. Please confirm that:

  1. No cell values were dropped or misaligned during the column restructuring
  2. The compatibility assertions for the three new parallelism columns reflect the intended behavior
  3. Values like "Untested" for newer feature combinations (e.g., LoRA, Slide Window Attention with EAGLE-3 variants) are intentional and complete

You can verify by comparing the final result against the previous version in the repository history (e.g., git diff HEAD~1 docs/source/features/feature-combination-matrix.md), ensuring no data corruption occurred during the merge.

@pcastonguay
Copy link
Collaborator Author

@laikhtewari @schetlur-nv @juney-nvidia do you know on top of your head which TP, PP, EP feature combinations are not supported?

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
@pcastonguay
Copy link
Collaborator Author

/bot skip --comment "Doc update only"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #28998 [ skip ] triggered by Bot. Commit: 8055f07

@tensorrt-cicd
Copy link
Collaborator

PR_Github #28998 [ skip ] completed with state SUCCESS. Commit: 8055f07
Skipping testing for commit 8055f07

@pcastonguay
Copy link
Collaborator Author

@juney-nvidia @laikhtewari would you mind reviewing and approving if you're ok with the changes? Thanks.

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
@pcastonguay
Copy link
Collaborator Author

/bot skip --comment "Doc update only"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #30911 [ skip ] triggered by Bot. Commit: 9d32b88

@tensorrt-cicd
Copy link
Collaborator

PR_Github #30911 [ skip ] completed with state SUCCESS. Commit: 9d32b88
Skipping testing for commit 9d32b88

@pcastonguay pcastonguay merged commit e8cceb0 into NVIDIA:main Jan 7, 2026
5 checks passed
videodanchik pushed a commit to videodanchik/TensorRT-LLM that referenced this pull request Jan 14, 2026
…VIDIA#9849)

Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Daniil Kulko <kulkodaniil@gmail.com>
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.

3 participants