feat: add BLS decoupled response iterator's cancel() method for the request cancellation #398
Conversation
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
adjust the comments title add finished check rename function adjust comment comment comment fix fix fix readme fix comments fix leak
richardhuo-nv
requested review from
kthui,
rmccorm4,
krishung5,
yinggeh and
ziqif-nv
20 tasks
richardhuo-nv
force-pushed
the
rihuo/add_bls_decoupled_cancel
branch
from
4aed0b9 to
a6a1a00
Compare
kthui
reviewed
Mar 25, 2025
kthui
reviewed
Mar 26, 2025
kthui
approved these changes
Mar 31, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What does the PR do?
Adding a cancel() method to the BLS decoupled response iterator, so that it will be able to cancel the Triton server inference request corresponding to the response iterator if the stub process gets the enough response from the response iterator.
Due to each stub InferenceRequest object can create multiple BLS Triton Server inference requests, so adding cancel() to the response iterator would be more feasible to manage cancelling individual request rather than cancelling all requests generated with the stub InferenceRequest object.
More details can be found in the change of the README.md
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/server#8097
Where should the reviewer start?
The major changes are on the python backend process, essentially the request executor. The major changes
Test plan:
25879687
Caveats:
Background
This feature is useful for stopping long inference requests, such as those from auto-generative large language models, which may run for an indeterminate amount of time and consume significant server resources.
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
https://jirasw.nvidia.com/browse/DLIS-7831