fix: cancel KVTask immediately when match/put condition not met to prevent memory leak#176
Open
xianweihuihuan wants to merge 2 commits into
Open
Conversation
Contributor
Author
|
Updated: the get path ( |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
In
_get_match()and the put path,flexkv_manager.get_match()/get_put()unconditionally creates a KVTask stored inKVTaskManager.tasks. When the match/put condition is not met(num_new_matched_tokens == 0 or num_unmatched_tokens == 0), the
task is neither added to
req_id_to_task_dictnor cancelled,causing it to leak in
self.tasksuntil ExpiringDict auto-expiresit after 30 minutes.
Under high concurrency with frequent cache misses, each request
produces a leaked KVTask holding
token_ids,slot_mapping, andtoken_maskarrays, leading to significant memory pressure.Fix
Call
self.flexkv_manager.cancel(task_ids=[task_id])immediatelyin the early-return branches where the task would otherwise be
abandoned, ensuring prompt cleanup of task resources.