KEMBAR78
[NvBug 5378370] fix: Fix alltoall for llama4 (apply_router_weight_on_input=True) by syuoni · Pull Request #5902 · NVIDIA/TensorRT-LLM · GitHub
Skip to content

Conversation

@syuoni
Copy link
Collaborator

@syuoni syuoni commented Jul 10, 2025

[NvBug 5378370] fix: Fix alltoall for llama4 (apply_router_weight_on_input=True)

LLaMA 4 has apply_router_weight_on_input=True, which leads to token_final_scales=None.

This PR fixes all alltoall paths for token_final_scales=None.

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.

@syuoni syuoni requested a review from a team as a code owner July 10, 2025 05:21
@syuoni syuoni requested a review from symphonylyh July 10, 2025 05:21
@syuoni
Copy link
Collaborator Author

syuoni commented Jul 10, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11507 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11507 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8514 completed with status: 'FAILURE'

@syuoni
Copy link
Collaborator Author

syuoni commented Jul 10, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11552 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11552 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8553 completed with status: 'SUCCESS'

syuoni added 5 commits July 11, 2025 01:45
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
@syuoni syuoni force-pushed the fix-alltoall-llama4 branch from c82471f to 8b6b195 Compare July 11, 2025 01:52
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11586 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11586 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8580 completed with status: 'FAILURE'

@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run --disable-fail-fast

2 similar comments
@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run --disable-fail-fast

@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11612 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11613 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11612 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11614 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11613 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11614 [ run ] completed with state FAILURE

@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run

1 similar comment
@syuoni
Copy link
Collaborator Author

syuoni commented Jul 11, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11659 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11659 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8634 completed with status: 'FAILURE'

@syuoni
Copy link
Collaborator Author

syuoni commented Jul 12, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #11691 [ run ] triggered by Bot

@syuoni syuoni enabled auto-merge (squash) July 12, 2025 06:33
@tensorrt-cicd
Copy link
Collaborator

PR_Github #11691 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8654 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@syuoni syuoni merged commit bc1d4fb into NVIDIA:main Jul 12, 2025
3 checks passed
@syuoni syuoni deleted the fix-alltoall-llama4 branch July 31, 2025 03:28
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