Skip to content

Conversation

@yizhang-nv
Copy link
Member

@yizhang-nv yizhang-nv commented Jul 10, 2025

PR title

MOE allreduce uses IPC memory, which cannot be used on a multi-node system. This pr disables the finalize moe allreduce kernel for non p2p supported systems.

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.

Details

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.

@yizhang-nv yizhang-nv requested review from a team as code owners July 10, 2025 12:48
@yizhang-nv
Copy link
Member Author

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-1,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-2,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-3,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-4"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11551 [ run ] triggered by Bot

@yizhang-nv yizhang-nv changed the title fix: Disable moe allreduce for multi node [nvbugs/5368410][fix] Disable moe allreduce for multi node Jul 10, 2025
@yizhang-nv
Copy link
Member Author

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-1,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-2,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-3,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-4"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11558 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11551 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11558 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #221 (Partly Tested) completed with status: 'FAILURE'

Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
@yizhang-nv
Copy link
Member Author

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-1,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-2,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-3,GB200-8_GPUs-2_Nodes-PyTorch-[Post-Merge]-4"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11582 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11582 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #223 (Partly Tested) completed with status: 'SUCCESS'

@yizhang-nv
Copy link
Member Author

/bot run --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11611 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11611 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #224 completed with status: 'FAILURE'

@yizhang-nv
Copy link
Member Author

/bot run --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11639 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11639 [ run ] completed with state FAILURE

@yizhang-nv
Copy link
Member Author

/bot run --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11679 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11679 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #235 completed with status: 'SUCCESS'

@yizhang-nv yizhang-nv merged commit 332a65b into NVIDIA:release/0.21 Jul 14, 2025
3 checks passed
Wanli-Jiang pushed a commit to Wanli-Jiang/TensorRT-LLM that referenced this pull request Jul 17, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
dc3671 pushed a commit to dc3671/TensorRT-LLM that referenced this pull request Jul 21, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
dc3671 pushed a commit to dc3671/TensorRT-LLM that referenced this pull request Jul 21, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
dc3671 pushed a commit to dc3671/TensorRT-LLM that referenced this pull request Jul 22, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
dc3671 pushed a commit that referenced this pull request Jul 22, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
NVShreyas pushed a commit to NVShreyas/TensorRT-LLM that referenced this pull request Jul 28, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
Ransiki pushed a commit to Ransiki/TensorRT-LLM that referenced this pull request Jul 29, 2025
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Ransiki Zhang <ransikiz@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.

3 participants