KEMBAR78
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices by VALLIS-NERIA · Pull Request #7568 · NVIDIA/TensorRT-LLM · GitHub
Skip to content

Conversation

@VALLIS-NERIA
Copy link
Collaborator

@VALLIS-NERIA VALLIS-NERIA commented Sep 5, 2025

Summary by CodeRabbit

  • New Features

    • Added broad SM103 (Blackwell) support across FP4/FP8 GEMM, FMHA, MLA, MOE, and dispatchers (treated as SM100 family).
    • Improved beam search with native half-precision variant.
    • Enhanced FP8/FP4 paths and default configs for SM103.
  • Bug Fixes

    • Stability fixes in attention and multimodal paths (tensor cloning, reductions) and improved error messaging.
    • More robust architecture detection (SM100 family).
  • Chores

    • Upgraded toolchain and containers: CUDA 13.0, TensorRT 10.13, PyTorch 2.8, CMake 4.0.3; refreshed dependencies.
  • Tests

    • Expanded multi-GPU test matrices (including DGX/GB300) and updated gating/skips for SM103 and FP4/FP8.

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

  • 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.

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.

VALLIS-NERIA and others added 30 commits August 6, 2025 14:24
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
infra: upgrade to DLFW 25.08-pre and TRT 10.13.2.4

See merge request ftp/tekit!9657

Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Fix and waive to clean L0

See merge request ftp/tekit!9660

Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
…u13'

infra: Support build for both CU12 and CU13

See merge request ftp/tekit!9665

Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
…n_0819

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
…n_0819

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
…n_0819

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@tensorrt-cicd
Copy link
Collaborator

PR_Github #18539 [ run ] completed with state ABORTED

@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18546 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18540 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #13916 (Blue Ocean) completed with status: ABORTED

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18559 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18546 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #13921 (Blue Ocean) completed with status: ABORTED

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18569 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18559 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #13933 (Blue Ocean) completed with status: ABORTED

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18590 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18569 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #13941 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18590 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13954 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot reuse-pipeline

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18676 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18676 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #18590 for commit 0192299

@litaotju litaotju merged commit c076a02 into main Sep 16, 2025
8 checks passed
@litaotju litaotju deleted the feat/b300_cu13 branch September 16, 2025 01:56
@chzblych chzblych restored the feat/b300_cu13 branch September 16, 2025 04:10
Wong4j pushed a commit to Wong4j/TensorRT-LLM that referenced this pull request Sep 20, 2025
…7568)

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: xiweny <13230610+VALLIS-NERIA@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Daniel Stokes <dastokes@nvidia.com>
Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
MrGeva pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Sep 21, 2025
…7568)

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: xiweny <13230610+VALLIS-NERIA@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Daniel Stokes <dastokes@nvidia.com>
Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
symphonylyh pushed a commit to symphonylyh/TensorRT-LLM that referenced this pull request Oct 15, 2025
…7568)

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: xiweny <13230610+VALLIS-NERIA@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Daniel Stokes <dastokes@nvidia.com>
Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@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.