Skip to content

test: [TRTLLM-4000] Port multi GPU changes to GitHub - #3027

Merged
Funatiq merged 1 commit into
NVIDIA:mainfrom
DomBrown:users/domb/split_cpp_multi_gpu
Mar 26, 2025
Merged

Funatiq merged 1 commit into
NVIDIA:mainfrom
DomBrown:users/domb/split_cpp_multi_gpu

Conversation

@DomBrown

Copy link
Copy Markdown
Collaborator

CI for multi GPU tests in C++ is too coarse grained if you need to re-run after a failure. This MR splits the cases up a bit. We may split further in later MRs

@DomBrown DomBrown added the Infra <NV>automated tests, build checks, github actions, system stability & efficiency. label Mar 24, 2025
@DomBrown
DomBrown requested review from Funatiq and jdebache March 24, 2025 11:26
@DomBrown DomBrown self-assigned this Mar 24, 2025
@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 24, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #293 [ run ] triggered by Bot

@juney-nvidia juney-nvidia changed the title [TRTLLM-4000] Port multi GPU changes to GitHub test: [TRTLLM-4000] Port multi GPU changes to GitHub Mar 24, 2025
@niukuo

niukuo commented Mar 24, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #293 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #282 completed with status: 'FAILURE'

@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 24, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #305 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 24, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #305 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #290 completed with status: 'FAILURE'

@DomBrown
DomBrown force-pushed the users/domb/split_cpp_multi_gpu branch from 7a21c0f to c3729e9 Compare March 24, 2025 20:31
@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 24, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #328 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #328 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #308 completed with status: 'FAILURE'

@QiJune

QiJune commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

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

@QiJune
QiJune self-requested a review March 25, 2025 05:35
@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #381 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #381 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #341 completed with status: 'FAILURE'

@DomBrown

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #403 [ run ] triggered by Bot

@DomBrown

Copy link
Copy Markdown
Collaborator Author

/bot kill

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #422 [ kill ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #403 [ run ] completed with state ABORTED

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #422 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit defc3c3

@DomBrown
DomBrown force-pushed the users/domb/split_cpp_multi_gpu branch from defc3c3 to 9758d17 Compare March 25, 2025 12:37
@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #435 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #435 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #372 completed with status: 'FAILURE'

@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #451 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #451 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #386 completed with status: 'FAILURE'

@DomBrown
DomBrown force-pushed the users/domb/split_cpp_multi_gpu branch from 9758d17 to bbd3dac Compare March 25, 2025 20:31
@DomBrown

Copy link
Copy Markdown
Collaborator Author

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

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #467 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #467 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #400 completed with status: 'FAILURE'

@DomBrown
DomBrown force-pushed the users/domb/split_cpp_multi_gpu branch from bbd3dac to 6c5e65c Compare March 26, 2025 11:19
@DomBrown

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #578 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #578 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #493 completed with status: 'SUCCESS'

@Funatiq
Funatiq enabled auto-merge (squash) March 26, 2025 21:22
@Funatiq
Funatiq force-pushed the users/domb/split_cpp_multi_gpu branch from 6c5e65c to 97c4bc4 Compare March 26, 2025 21:22
@Funatiq

Funatiq commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

/bot reuse-pipeline

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
@Funatiq
Funatiq force-pushed the users/domb/split_cpp_multi_gpu branch from 97c4bc4 to adf7028 Compare March 26, 2025 21:41
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #614 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #614 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #578 for commit adf7028

@Funatiq
Funatiq merged commit 60d4dac into NVIDIA:main Mar 26, 2025
@DomBrown
DomBrown deleted the users/domb/split_cpp_multi_gpu branch April 10, 2025 14:23
wu1du2 pushed a commit to wu1du2/TensorRT-LLM that referenced this pull request May 11, 2025
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Infra <NV>automated tests, build checks, github actions, system stability & efficiency.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants