Skip to content

Conversation

@ixlmar
Copy link
Collaborator

@ixlmar ixlmar commented Sep 22, 2025

Description

This small improvement generalizes the pre-existing shortcut to reduce data movement when the request sampling groups are contiguous within the batch. This is relevant, e.g., if no requests share the same sampling parameters.

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

  • 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.

Summary by CodeRabbit

  • New Features
    • Introduced batched, strategy-aware sampling (top-k, top-p, top-k+top-p, greedy) with improved efficiency and draft-probability support.
    • Added optional load_format to decoding configuration.
  • Refactor
    • Removed the mixed sampler option from user/configuration surfaces; sampling now unified under the new framework.
    • Adjusted chain-drafter enablement logic to align with new greedy-draft controls.
  • Chores
    • Raised minimum Python requirement to 3.10.
  • Evaluation
    • Set temperature=0 in JSON-mode and MMLU sample generation for consistent behavior.

@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19584 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19584 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #14726 completed with status: 'FAILURE'

@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19589 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19589 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #14731 completed with status: 'FAILURE'

@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19594 [ run ] triggered by Bot

@ixlmar ixlmar force-pushed the perf/sampling-contiguous-batches branch from fb76f2a to 96457be Compare September 22, 2025 13:58
@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19599 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19594 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #14735 (Blue Ocean) completed with status: ABORTED

@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot kill

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19616 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19599 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #14739 (Blue Ocean) completed with status: ABORTED

@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 22, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19616 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 96457be

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19618 [ run ] triggered by Bot

@ixlmar ixlmar marked this pull request as ready for review September 23, 2025 05:44
@ixlmar ixlmar requested review from a team as code owners September 23, 2025 05:44
@ixlmar ixlmar marked this pull request as ready for review September 24, 2025 09:09
@ixlmar ixlmar requested a review from dcampora September 24, 2025 09:10
@tensorrt-cicd
Copy link
Collaborator

PR_Github #19783 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19783 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #14885 completed with status: 'FAILURE'

@ixlmar ixlmar force-pushed the perf/sampling-contiguous-batches branch from 0e0a9b5 to 3507535 Compare September 24, 2025 13:06
@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19808 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19808 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #14904 completed with status: 'FAILURE'

@ixlmar ixlmar force-pushed the perf/sampling-contiguous-batches branch from 3507535 to c074ad8 Compare September 24, 2025 15:06
@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19821 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19821 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14913 completed with status: 'FAILURE'

@ixlmar ixlmar force-pushed the perf/sampling-contiguous-batches branch from c074ad8 to b99bfae Compare September 24, 2025 16:55
@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19830 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19830 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14920 completed with status: 'FAILURE'

@ixlmar ixlmar force-pushed the perf/sampling-contiguous-batches branch from b99bfae to 057d988 Compare September 25, 2025 07:39
@ixlmar
Copy link
Collaborator Author

ixlmar commented Sep 25, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19911 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19911 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14987 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@ixlmar ixlmar requested a review from DomBrown September 25, 2025 16:39
Copy link
Collaborator

@DomBrown DomBrown left a comment

Choose a reason for hiding this comment

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

LGTM

@DomBrown DomBrown merged commit a0d489a into NVIDIA:main Sep 29, 2025
5 checks passed
@ixlmar ixlmar deleted the perf/sampling-contiguous-batches branch September 29, 2025 12:33
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 1, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
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