Skip to content

Conversation

ixlmar
Copy link
Collaborator

@ixlmar ixlmar commented May 14, 2025

chore: restore symmetry of worker start/shutdown
chore: fix return type of cal_max_tokens
chore: type some more return values
fix: free resources before re-claiming

PR title

Please write the PR title by following template:

[JIRA ticket link/nvbug link/github issue link][fix/feat/doc/infra/...] <summary of this PR>

For example, assume I have a PR hope to support a new feature about cache manager of Jira TRTLLM-1000 ticket, it would be like

[TRTLLM-1000][feat] Support a new feature about cache manager

Description

This PR summarizes a few minor improvements to create_py_executor.

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.

@ixlmar ixlmar requested review from DomBrown and dcampora May 14, 2025 10:47
@ixlmar ixlmar marked this pull request as ready for review May 14, 2025 10:51
@ixlmar
Copy link
Collaborator Author

ixlmar commented May 14, 2025

/bot run

Copy link
Collaborator

@DomBrown DomBrown left a comment

Choose a reason for hiding this comment

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

I would like to be absolutely sure that these None checks are not required before approving this (see comments).

I agree that kv_cache_manager is not None seems un-necessary in the places you have removed it. I'm just wondering if there is some 'side-effect' reasons for that check being in place. If not then fine :)

Otherwise looks good

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5165 [ run ] triggered by Bot

@ixlmar ixlmar requested a review from DomBrown May 14, 2025 13:02
Copy link
Collaborator

@DomBrown DomBrown left a comment

Choose a reason for hiding this comment

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

Comments addressed. LGTM

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5165 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3766 completed with status: 'FAILURE'

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5286 [ run ] triggered by Bot

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot kill

@ixlmar ixlmar force-pushed the chore/kv-cache-allocation branch from 85590c1 to e0760b4 Compare May 15, 2025 07:09
@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5293 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5294 [ ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5286 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5293 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit e0760b4

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5295 [ run ] triggered by Bot

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5325 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5295 [ run ] completed with state ABORTED
/LLM/main/L0_MergeRequest_PR pipeline #3867 completed with status: 'FAILURE'

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5325 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3883 completed with status: 'FAILURE'

@ixlmar ixlmar force-pushed the chore/kv-cache-allocation branch from e0760b4 to c75ab28 Compare May 15, 2025 15:40
@ixlmar
Copy link
Collaborator Author

ixlmar commented May 15, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5367 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5367 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3918 completed with status: 'FAILURE'

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 16, 2025

/bot run

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 16, 2025

/bot kill

chore: restore symmetry of worker start/shutdown
chore: fix return type of cal_max_tokens
chore: type some more return values
fix: free resources before re-claiming

Signed-off-by: ixlmar <[email protected]>
@ixlmar ixlmar force-pushed the chore/kv-cache-allocation branch from c75ab28 to 6666996 Compare May 16, 2025 08:15
@tensorrt-cicd
Copy link
Collaborator

PR_Github #5484 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5485 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5484 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5485 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 6666996

@ixlmar
Copy link
Collaborator Author

ixlmar commented May 16, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5487 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5487 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4003 completed with status: 'SUCCESS'

@DomBrown DomBrown merged commit 13b6140 into NVIDIA:main May 16, 2025
3 checks passed
@ixlmar ixlmar deleted the chore/kv-cache-allocation branch May 16, 2025 15:36
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