GitLab

Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: tovam <tovam@pliops.com>
Signed-off-by: Tova Movshovitz <tovam@pliops.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

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>

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

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>

Signed-off-by: Max Hu <hyoung2991@gmail.com>
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>

Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Alec S <10566873+alecsolder@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>

Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

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>

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>

Signed-off-by: LuminolT <lumischen01@gmail.com>
Signed-off-by: Lumis Chen <lumischen01@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

Signed-off-by: Yong Hoon Shin <yhshin@meta.com>

Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Signed-off-by: maang <maang_h@163.com>
Signed-off-by: maang-h <55082429+maang-h@users.noreply.github.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

Signed-off-by: jthomson04 <jwillthomson19@gmail.com>

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Mickael Seznec <mickael@mistral.ai>

Signed-off-by: Wushi Dong <dongws@meta.com>

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Signed-off-by: Bradley <bradley.b.pitt@gmail.com>

Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Co-authored-by: rongfu.leng <1275177125@qq.com>

Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

Signed-off-by: Nick Hill <nhill@redhat.com>

Introduces three new Prometheus histograms for fine-grained observability of KV cache residency behavior:

vllm:kv_block_lifetime_seconds — total lifetime from allocation to free
vllm:kv_block_idle_before_evict_seconds — idle duration before eviction
vllm:kv_block_reuse_gap_seconds — time between consecutive reuses of the same block

These metrics help operators analyze KV cache efficiency, reuse patterns, and eviction timing beyond simple utilization rates.

Implementation uses monotonic timestamps for accuracy, 1% sampling for minimal overhead (~48 bytes/block), and is fully thread-safe with zero runtime cost when disabled.

Two new runtime flags are introduced:

--kv-cache-metrics – enable KV cache residency metrics
--kv-cache-metrics-sample – control sampling ratio (default: 0.01)
Signed-off-by: Shivam <shivamprasad91@gmail.com>

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Co-authored-by: baonudesifeizhai <baonudesifeizhai@gmail.com>

Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>

Signed-off-by: Yifei Zhang <yifei.zhang1992@outlook.com>

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Signed-off-by: ganyi <ygan@amd.com>