Skip to content

Conversation

@rosenrodt
Copy link
Collaborator

@rosenrodt rosenrodt commented Dec 15, 2025

Summary by CodeRabbit

Release Notes

  • Chores
    • Updated pre-built kernel binary artifacts for optimized performance and compatibility.

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

Description

Credits to @davidclark-nv who did the main investigation and the kernel fix.

The NaN handling in #9377 had changed and it led to NaN propagation. The PR reverses that part of the change.

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: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
@rosenrodt
Copy link
Collaborator Author

/bot run

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Dec 15, 2025

📝 Walkthrough

Walkthrough

This PR updates Git LFS pointer metadata for over 100 CUDA binary kernel files (CUBINs) in the TensorRT-LLM batch matrix multiplication export directory. Each file's object ID (sha256 oid) and sometimes file size are updated, reflecting changes to the underlying compiled binary artifacts with no functional code modifications.

Changes

Cohort / File(s) Summary
TensorRT-LLM Batch Gemm CUBIN Exports (Bmm_E2m1 variants)
cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_E2m1_E2m1E2m1_Fp32_*_cubin.cpp (40+ files)
Git LFS pointer updates: object IDs (sha256 oid) and/or file sizes changed for compiled CUDA kernels. No code or logic changes.
TensorRT-LLM Batch Gemm CUBIN Exports (Bmm_MxE4m3 variants)
cpp/tensorrt_llm/kernels/trtllmGenKernels/batchedGemm/trtllmGen_bmm_export/cubins/Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_*_cubin.cpp (60+ files)
Git LFS pointer updates: object IDs (sha256 oid) and/or file sizes changed for compiled CUDA kernels. No code or logic changes.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Rationale: All changes are homogeneous, repetitive Git LFS metadata updates with identical patterns across 100+ files. No functional code logic, control flow, error handling, or public API changes are involved. Review consists of verifying pointer format consistency and confirming no unintended file mutations.

Possibly related PRs

  • NVIDIA/TensorRT-LLM#8200: Updates Git LFS pointer metadata for the same set of trtllmGen_bmm_export/cubins CUDA binary files; both PRs manage artifact versions for kernel compilations.

Suggested reviewers

  • djns99
  • byshiue
  • brb-nv

Pre-merge checks and finishing touches

❌ Failed checks (1 inconclusive)
Check name Status Explanation Resolution
Description check ❓ Inconclusive The PR description is incomplete and lacks critical details required by the template. Add a clear, detailed description of the issue and solution. Include specific information about which NaN handling change was reverted and why. Detail the test coverage confirming this fix resolves the accuracy issue mentioned in PR #9377.
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The PR title clearly and specifically identifies the main change: fixing an accuracy issue in TRTLLM MoE introduced by a previous PR, with proper reference to both the NVBugs ID and the related PR.
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.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #28340 [ run ] triggered by Bot. Commit: cf0e008

@rosenrodt rosenrodt requested a review from nekorobov December 15, 2025 07:10
@longlee0622 longlee0622 enabled auto-merge (squash) December 15, 2025 08:06
@tensorrt-cicd
Copy link
Collaborator

PR_Github #28340 [ run ] completed with state SUCCESS. Commit: cf0e008
/LLM/main/L0_MergeRequest_PR pipeline #21681 completed with status: 'SUCCESS'

@longlee0622 longlee0622 merged commit ad12b79 into NVIDIA:main Dec 15, 2025
10 of 11 checks passed
sherry-1001 pushed a commit to sherry-1001/TensorRT-LLM that referenced this pull request Dec 16, 2025
…uced in NVIDIA#9377 (NVIDIA#9999)

Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
codego7250 pushed a commit to codego7250/TensorRT-LLM that referenced this pull request Dec 19, 2025
…uced in NVIDIA#9377 (NVIDIA#9999)

Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.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.

4 participants