Skip to content

Conversation

Funatiq
Copy link
Collaborator

@Funatiq Funatiq commented May 6, 2025

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".

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.

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 6, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4228 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4228 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3019 completed with status: 'FAILURE'

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 6, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4241 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4241 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3030 completed with status: 'FAILURE'

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 6, 2025

/bot run --stage-list "H100_PCIe-CPP-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4259 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4259 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3046 (Partly Tested) completed with status: 'FAILURE'

@Funatiq Funatiq force-pushed the dev/remove_gpt_session branch from 8e1f7e9 to afa60f1 Compare May 7, 2025 08:22
@Funatiq
Copy link
Collaborator Author

Funatiq commented May 7, 2025

/bot run --stage-list "H100_PCIe-CPP-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4352 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4352 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3121 (Partly Tested) completed with status: 'SUCCESS'

@Funatiq Funatiq marked this pull request as ready for review May 7, 2025 13:32
@Funatiq Funatiq requested review from DomBrown and hypdeb May 7, 2025 13:32
Copy link
Collaborator

@hypdeb hypdeb left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good overall. Two small comments / questions:

  • Are we confident that we are not losing too much incidental testing by removing the gptSession tests?
  • I've encountered many symbols only referenced in the gptSession path. Are you sure you removed all of those, as they should be now unused.

@DomBrown
Copy link
Collaborator

DomBrown commented May 8, 2025

LGTM. Nice. Julien's questions are good ones, though.

@Funatiq Funatiq changed the title chore: Remove GptSession/V1 from TRT workflow [TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow May 8, 2025
@Funatiq Funatiq force-pushed the dev/remove_gpt_session branch from 3853388 to 71b4561 Compare May 12, 2025 09:55
@Funatiq
Copy link
Collaborator Author

Funatiq commented May 12, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4869 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4869 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3527 completed with status: 'FAILURE'

@Funatiq Funatiq force-pushed the dev/remove_gpt_session branch from 28392c0 to 1703a10 Compare May 12, 2025 20:50
@Funatiq
Copy link
Collaborator Author

Funatiq commented May 12, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4906 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4906 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3558 completed with status: 'FAILURE'

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 13, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5001 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5001 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3634 completed with status: 'FAILURE'

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5020 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5020 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3652 completed with status: 'FAILURE'

Funatiq added 13 commits May 13, 2025 18:32
- Updated `validateContextLogits` and `validateGenerationLogits` functions to remove the `batchingType` parameter.
- Adjusted related test functions to reflect the changes in parameter lists.
- Cleaned up the instantiation of test cases to eliminate unnecessary batchingType references.

Signed-off-by: Robin Kobus <[email protected]>
@Funatiq Funatiq force-pushed the dev/remove_gpt_session branch from ff477bb to a79f641 Compare May 13, 2025 16:32
@Funatiq
Copy link
Collaborator Author

Funatiq commented May 13, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5044 [ run ] triggered by Bot

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 13, 2025

Are we confident that we are not losing too much incidental testing by removing the gptSession tests?

Yes, the models are also covered in TrtModelRealDecoderTest and ExecutorTest. The only models that we lose are those that do not support IFB anyway.

I've encountered many symbols only referenced in the gptSession path. Are you sure you removed all of those, as they should be now unused.

I cleaned up everything I could find.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5044 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3672 completed with status: 'FAILURE'

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 14, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5149 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5149 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3755 completed with status: 'FAILURE'

@Funatiq
Copy link
Collaborator Author

Funatiq commented May 14, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5193 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5193 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3790 completed with status: 'SUCCESS'

@Funatiq Funatiq merged commit d31fefd into NVIDIA:main May 14, 2025
3 checks passed
@Funatiq Funatiq deleted the dev/remove_gpt_session branch May 27, 2025 10:55
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.

4 participants