Skip to content

feat: Add support for MXFP8xMXFP4 in pytorch #5535

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 6, 2025

Conversation

djns99
Copy link
Collaborator

@djns99 djns99 commented Jun 27, 2025

PR title

Description

Please explain the issue and the solution in short.

Test Coverage

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 [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

Launch build/test pipelines. All previously running jobs will be killed.

--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 "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, 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.

--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. Will also run 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-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md.

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.

@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch 9 times, most recently from 4377d21 to b4e47c4 Compare July 1, 2025 03:12
@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from b636673 to 3009520 Compare July 2, 2025 04:21
@djns99 djns99 marked this pull request as ready for review July 2, 2025 04:58
@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from 2538b44 to 84a864f Compare July 2, 2025 05:12
@djns99
Copy link
Collaborator Author

djns99 commented Jul 2, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10569 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10569 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7822 completed with status: 'FAILURE'

@djns99 djns99 requested a review from a team as a code owner July 2, 2025 09:58
@djns99 djns99 requested a review from dongxuy04 July 2, 2025 09:58
@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from 20ed047 to 14b6e51 Compare July 2, 2025 09:58
@djns99
Copy link
Collaborator Author

djns99 commented Jul 2, 2025

/bot run --disable-fail-fast

@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from 14b6e51 to a3b07ed Compare July 2, 2025 21:14
@djns99
Copy link
Collaborator Author

djns99 commented Jul 2, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10703 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10703 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7912 completed with status: 'FAILURE'

@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from a3b07ed to 566b5ad Compare July 3, 2025 04:14
@djns99
Copy link
Collaborator Author

djns99 commented Jul 3, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10751 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10751 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7942 completed with status: 'FAILURE'

@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from 566b5ad to 6f451db Compare July 3, 2025 22:04
@djns99
Copy link
Collaborator Author

djns99 commented Jul 3, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10873 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10873 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8037 completed with status: 'FAILURE'

Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
@djns99 djns99 force-pushed the user/djns99/mxfp8_moe_input branch from 6f451db to ff8d85e Compare July 4, 2025 04:27
@djns99
Copy link
Collaborator Author

djns99 commented Jul 4, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10926 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10926 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8076 completed with status: 'SUCCESS'

@hlu1 hlu1 merged commit ec6c7df into NVIDIA:main Jul 6, 2025
3 checks passed
zhou-yuxin pushed a commit to zhou-yuxin/TensorRT-LLM that referenced this pull request Jul 15, 2025
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
Signed-off-by: Yuxin <yuxinz@nvidia.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.

5 participants