Conversation
bdc7688 to
0552591
Compare
70d09a8 to
85bc836
Compare
Collaborator
Yes, the calculation of last_uncached_pos should be handled correctly in the EAGLE fix, or it may cause memory leak issue. This preempt case is not tested in the previous fix. |
merrymercy
approved these changes
Oct 15, 2025
ByronHsu
approved these changes
Oct 15, 2025
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Prepration for mem_cache V2.
This PR aims to simpify the kv cache free logic
Modifications
cache_finished_reqis_insertto skip inserting to treetoken_idsto support preempting a prefill request.release_reqby usingcache_finished_reqwith no insertrelease_reqdoes not consider the eagle radix tree fix cc @ispobock to confirmAccuracy Tests
Benchmarking and Profiling
Checklist