[https://nvbugs/5973801][fix] exclude subproc_worker_timer from thread leak checks#12286
Merged
MrGeva merged 3 commits intoNVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom Mar 17, 2026
nv-auto-deploy:eg/fixthreadleaknv-auto-deploy/TensorRT-LLM:eg/fixthreadleakCopy head branch name to clipboard
Merged
[https://nvbugs/5973801][fix] exclude subproc_worker_timer from thread leak checks#12286MrGeva merged 3 commits intoNVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom nv-auto-deploy:eg/fixthreadleaknv-auto-deploy/TensorRT-LLM:eg/fixthreadleakCopy head branch name to clipboard
MrGeva merged 3 commits intoNVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom
nv-auto-deploy:eg/fixthreadleaknv-auto-deploy/TensorRT-LLM:eg/fixthreadleakCopy head branch name to clipboard
Conversation
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
Collaborator
Author
|
/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1" |
Contributor
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Comment Tip You can customize the tone of the review comments and chat replies.Configure the |
Collaborator
|
PR_Github #39273 [ run ] triggered by Bot. Commit: |
lucaslie
approved these changes
Mar 17, 2026
Collaborator
|
PR_Github #39273 [ run ] completed with state |
limin2021
pushed a commit
to limin2021/TensorRT-LLM
that referenced
this pull request
Mar 19, 2026
…d leak checks (NVIDIA#12286) Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
longcheng-nv
pushed a commit
to longcheng-nv/TensorRT-LLM
that referenced
this pull request
Mar 31, 2026
…d leak checks (NVIDIA#12286) Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
All leak <Thread(subproc_worker_timer, ...)> from torch/_inductor/compile_worker/timer.py. The
timer is created when quiesce_async_compile_pool is enabled (via NVIDIA's internal justknob
system in CI). After the compile pool shuts down, timer.quit() sets a flag, but the thread is in
a 30-second sleep and won't check the flag until after the test ends.
The fix — adding subproc_worker_timer to threadleak_exclude in tests/unittest/pytest.ini —
follows the exact same precedent as InductorSubproc (already excluded, same pool, same
justification: benign daemon thread internal to PyTorch inductor). This single-line change covers
all 7 failing test instances across all 3 GPU environments.
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.