- 07 Dec, 2025 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 06 Dec, 2025 2 commits
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
- 05 Dec, 2025 3 commits
-
-
Ilya Markov authored
Signed-off-by:
Luka Govedič <lgovedic@redhat.com> Signed-off-by:
Luka Govedič <ProExpertProg@users.noreply.github.com> Signed-off-by:
ilmarkov <markovilya197@gmail.com> Signed-off-by:
Luka Govedič <luka.govedic@gmail.com> Signed-off-by:
ProExpertProg <lgovedic@redhat.com> Co-authored-by:
Luka Govedič <lgovedic@redhat.com> Co-authored-by:
Luka Govedič <ProExpertProg@users.noreply.github.com> Co-authored-by:
Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Co-authored-by:
Luka Govedič <luka.govedic@gmail.com>
-
Nick Hill authored
Currently, when requests are cancelled while executing their final step, "completion" is handled based on normal stop processing (e.g. length or stop token), so the abort has no effect. This is typically not a problem, but when a kv connector is involved it thinks the request completed successfully rather than being aborted. This is problematic for disaggregated prefill which will free kv cache blocks if the request was aborted but not if it completed successfully—since the cancelled request will never be sent to the decode side, kv cache blocks remain pinned until the fall-back timeout expires. The problem is exacerbated when many requests are cancelled and/or there are large prefills whose forward pass takes a long time (since the window is bigger). This PR fixes the problem by processing pending aborts immediately prior to processing model output each step; we process only aborts, not new requests, since it's preferable for latency to process model outputs before new incoming requests. Fixes #26400. Signed-off-by:Nick Hill <nhill@redhat.com>
-
Max Hu authored
Signed-off-by:
Max Hu <hyoung2991@gmail.com> Signed-off-by:
Max Hu <maxhu@nvidia.com> Co-authored-by:
Max Hu <maxhu@nvidia.com>
-
- 04 Dec, 2025 4 commits
-
-
Lucas Wilkinson authored
Signed-off-by:Lucas Wilkinson <lwilkins@redhat.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
wang.yuqi authored
Signed-off-by:
wang.yuqi <noooop@126.com> Signed-off-by:
wang.yuqi <yuqi.wang@daocloud.io> Co-authored-by:
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
-
- 03 Dec, 2025 3 commits
-
-
Yong Hoon Shin authored
Signed-off-by:Yong Hoon Shin <yhshin@meta.com>
-
Arpit Khandelwal authored
Signed-off-by:
arpitkh101 <arpit5khandelwal@gmail.com> Co-authored-by:
Luka Govedič <ProExpertProg@users.noreply.github.com>
-
Lucas Wilkinson authored
Signed-off-by:Lucas Wilkinson <lwilkins@redhat.com>
-
- 02 Dec, 2025 2 commits
-
-
Wushi Dong authored
Signed-off-by:Wushi Dong <dongws@meta.com>
-
Zhuohan Li authored
Signed-off-by:
Zhuohan Li <zhuohan123@gmail.com> Signed-off-by:
Nick Hill <nhill@redhat.com> Co-authored-by:
Nick Hill <nhill@redhat.com>
-
- 01 Dec, 2025 1 commit
-
-
Yifei Zhang authored
Signed-off-by:Yifei Zhang <yifei.zhang1992@outlook.com>
-
- 30 Nov, 2025 3 commits
-
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Vensen authored
Signed-off-by:
vensen <vensenmu@gmail.com> Co-authored-by:
TJian <tunjian.tan@embeddedllm.com>
-
- 29 Nov, 2025 7 commits
-
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Jee Jee Li authored
Signed-off-by:
Jee Jee Li <pandaleefree@gmail.com> Co-authored-by:
Cyrus Leung <tlleungac@connect.ust.hk>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Lucas Wilkinson authored
Signed-off-by:Lucas Wilkinson <lwilkins@redhat.com>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
- 28 Nov, 2025 2 commits
-
-
Benjamin Chislett authored
Signed-off-by:
Benjamin Chislett <bchislett@nvidia.com> Signed-off-by:
Benjamin Chislett <chislett.ben@gmail.com>
-
Didier Durand authored
Signed-off-by:Didier Durand <durand.didier@gmail.com>
-
- 27 Nov, 2025 10 commits
-
-
Lucas Wilkinson authored
Signed-off-by:Lucas Wilkinson <lwilkins@redhat.com>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Matthew Bonanni authored
Signed-off-by:Matthew Bonanni <mbonanni@redhat.com>
-
Didier Durand authored
Signed-off-by:Didier Durand <durand.didier@gmail.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Morrison Turnansky authored
Signed-off-by:
morrison-turnansky <mturnans@redhat.com> Signed-off-by:
adabeyta <aabeyta@redhat.com> Signed-off-by:
Morrison Turnansky <mturnans@redhat.com> Co-authored-by:
adabeyta <aabeyta@redhat.com> Co-authored-by:
Luka Govedič <ProExpertProg@users.noreply.github.com> Co-authored-by:
Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Woosuk Kwon authored
Signed-off-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
- 26 Nov, 2025 2 commits
-
-
Johnny Yang authored
Signed-off-by:Johnny Yang <johnnyyang@google.com>
-
Lucas Wilkinson authored
-