Skip to content

Conversation

jmydurant
Copy link
Collaborator

Description

support nvfp4 model and fp8 kv cache for MLA chunked prefill. It contains some commits based on #4651

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.

@jmydurant
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9861 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9861 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7274 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@PerkzZheng
Copy link
Collaborator

@jmydurant can you help rebase this branch to the latest main ? it seems to contain many commits from #4651

@jmydurant jmydurant force-pushed the user/WIP/fp8kvcache branch from 9f3e9e3 to 295b1ac Compare June 26, 2025 03:28
@jmydurant
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9962 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9962 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7350 completed with status: 'SUCCESS'

@kaiyux kaiyux marked this pull request as ready for review June 26, 2025 08:21
@kaiyux kaiyux requested review from a team as code owners June 26, 2025 08:21
@kaiyux kaiyux changed the title [TRTLLM-3602][feat]Draft: support nvfp4 model and fp8 kv cache for MLA chunked prefill (Blackwell) [TRTLLM-3602][feat] support nvfp4 model and fp8 kv cache for MLA chunked prefill (Blackwell) Jun 26, 2025
@jmydurant
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10022 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10022 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7394 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@jmydurant
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10037 [ run ] triggered by Bot

@kaiyux
Copy link
Member

kaiyux commented Jun 26, 2025

/bot skip --comment "the last commit is just modifying comment, no need to rerun pipeline"

@kaiyux kaiyux enabled auto-merge (squash) June 26, 2025 14:07
@tensorrt-cicd
Copy link
Collaborator

PR_Github #10042 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10037 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10042 [ skip ] completed with state SUCCESS
Skipping testing for commit 3604b9c

@kaiyux kaiyux merged commit 8836990 into NVIDIA:main Jun 26, 2025
3 checks passed
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 9, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 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.

5 participants