reviewer: limit max concurrency semaphore - #359
Open
mchehab wants to merge 1 commit into
Open
Conversation
The reviewer code works with two semaphores: - semaphore, which reflects what's there at concurrency; - llm_semaphore, which is initialized to have 3 times the value of concurrency. This is based on an estimation that an active patch review consumes ~3 LLM slots. Such model works when using cloud-based models, but when the models run locally, this must be aligned with the maximum queue size of the local engine. Add an extra optional parameter to allow adjusting such limit. Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Contributor
Author
|
@derekbarbosa This is per your request at #338: even after having it merged, it still makes sense to be able to optionally limit |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The reviewer code works with two semaphores:
This is based on an estimation that an active patch review consumes ~3 LLM slots.
Such model works when using cloud-based models, but when the models run locally, this must be aligned with the maximum queue size of the local engine.
Add an extra optional parameter to allow adjusting such limit.