[None][chore] Update feature combination matrix for SWA kv cache reuse #8529

eopXD · 2025-10-21T08:06:38Z

Summary by CodeRabbit

Documentation
- Updated feature comparison matrix to indicate Slide Window Attention is now available.

Description

SWA is now supported in the KV cache manager :)

Test Coverage

Documentation update, now test coverage needed.

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
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.

SWA is now supported in the KV cache manager :) Signed-off-by: eopXD <yuehtingc@nvidia.com>

eopXD · 2025-10-21T08:07:14Z

/bot run

coderabbitai · 2025-10-21T08:09:05Z

📝 Walkthrough

Walkthrough

Documentation update to the feature comparison matrix marking Slide Window Attention as completed (status changed from WIP to Yes).

Changes

Cohort / File(s)	Change Summary
Documentation Status Update `docs/source/features/feature-combination-matrix.md`	Updated Slide Window Attention feature status from WIP to Yes in the feature comparison matrix

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The PR title "[None][chore] Update feature combination matrix for SWA kv cache reuse" directly and clearly summarizes the main change in the pull request. According to the raw summary, the changeset updates the feature comparison matrix documentation by marking Slide Window Attention (SWA) as "Yes" (from "WIP") for KV cache reuse support. The title correctly follows the repository's required format with the ticket identifier, type, and concise summary, and it is specific enough that a reviewer can understand the primary change without vagueness or noise.
Description Check	✅ Passed	The PR description follows the required template structure with all essential sections present: Description ("SWA is now supported in the KV cache manager :)"), Test Coverage ("Documentation update, now test coverage needed."), and a completed PR Checklist. While the Test Coverage section is brief and could be slightly clearer, it appropriately addresses the fact that this is a documentation-only change to a markdown file. The description is mostly complete and not off-topic, with the core information conveyed despite minimal elaboration.
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.

✨ Finishing touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent 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 c566890 and 2fd8eb8.

📒 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)

16-16: Documentation update approved.

The feature matrix correctly reflects that Slide Window Attention is now supported with KV Cache Reuse (row-column intersection updated from WIP to Yes). The change is consistent with the matrix structure and the PR objective.

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.}

QiJune

LGTM

tensorrt-cicd · 2025-10-21T08:12:36Z

PR_Github #22029 [ run ] triggered by Bot. Commit: 2fd8eb8

QiJune · 2025-10-21T08:16:11Z

/bot skip --comment "doc change"

tensorrt-cicd · 2025-10-21T08:21:39Z

PR_Github #22031 [ skip ] triggered by Bot. Commit: 2fd8eb8

tensorrt-cicd · 2025-10-21T08:21:40Z

PR_Github #22029 [ run ] completed with state ABORTED. Commit: 2fd8eb8
LLM/main/L0_MergeRequest_PR #16609 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd · 2025-10-21T08:41:42Z

PR_Github #22031 [ skip ] completed with state SUCCESS. Commit: 2fd8eb8
Skipping testing for commit 2fd8eb8

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com> Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

[None][chore] Update feature combination matrix

2fd8eb8

SWA is now supported in the KV cache manager :) Signed-off-by: eopXD <yuehtingc@nvidia.com>

eopXD requested a review from a team as a code owner October 21, 2025 08:06

eopXD requested review from Shixiaowei02 and kaiyux October 21, 2025 08:06

eopXD self-assigned this Oct 21, 2025

QiJune approved these changes Oct 21, 2025

View reviewed changes

eopXD enabled auto-merge (squash) October 21, 2025 08:11

eopXD merged commit 85088dc into NVIDIA:main Oct 21, 2025
8 of 9 checks passed

eopXD deleted the update-feature-combination-matrix-swa-kv-cache branch October 21, 2025 08:42

govind-ramnarayan pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Oct 21, 2025

[None][chore] Update feature combination matrix for SWA kv cache reuse (

bf0a20f

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 1, 2025

[None][chore] Update feature combination matrix for SWA kv cache reuse (

a6cab09

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[None][chore] Update feature combination matrix for SWA kv cache reuse (

fbdb264

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[None][chore] Update feature combination matrix for SWA kv cache reuse (

442febd

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[None][chore] Update feature combination matrix for SWA kv cache reuse (

5f9b593

NVIDIA#8529) Signed-off-by: eopXD <yuehtingc@nvidia.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[None][chore] Update feature combination matrix for SWA kv cache reuse #8529

[None][chore] Update feature combination matrix for SWA kv cache reuse #8529

Uh oh!

eopXD commented Oct 21, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

eopXD commented Oct 21, 2025

Uh oh!

coderabbitai bot commented Oct 21, 2025

Walkthrough

Changes

Estimated code review effort

Uh oh!

QiJune left a comment

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

QiJune commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[None][chore] Update feature combination matrix for SWA kv cache reuse #8529

[None][chore] Update feature combination matrix for SWA kv cache reuse #8529

Uh oh!

Conversation

eopXD commented Oct 21, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

eopXD commented Oct 21, 2025

Uh oh!

coderabbitai bot commented Oct 21, 2025

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

QiJune left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

QiJune commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

tensorrt-cicd commented Oct 21, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

eopXD commented Oct 21, 2025 •

edited by coderabbitai bot

Loading