refactor(hicache): simplify decode offload state bookkeeping - #37299
Merged
Merged
Conversation
hnyls2002
requested review from
ByronHsu,
Duyi-Wang,
HaiShaw,
ShangmingCai and
sogalin
as code owners
August 31, 2026 23:07
Collaborator
Author
|
/rerun-test registered/unit/disaggregation/test_specv2_kvcache_offloading.py registered/disaggregation/test_disaggregation_decode_offload.py |
Contributor
|
Results for 🚀 🚀 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #37026: derive the page-aligned prefill length instead of storing it in OffloadedState (removing the placeholder-state path in finalize_release_on_finish), key the per-request offload tables with weak references so a request released outside _release_finished_req is not pinned forever, and drop the unused start/end fields from ongoing_offload entries.
CI States
Latest PR Test (Base): 🚫 Run #33472996218
Latest PR Test (Extra): ❌ Run #33472995915
Latest PR Test (AMD ROCm 7.2): 🚫 Run #33472996029