- 09 Dec, 2025 1 commit
-
-
Victor Ziliang Peng authored
Signed-off-by:Ziliang Peng <ziliang@character.ai>
-
- 08 Dec, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-
- 03 Dec, 2025 1 commit
-
-
Yong Hoon Shin authored
Signed-off-by:Yong Hoon Shin <yhshin@meta.com>
-
- 02 Dec, 2025 1 commit
-
-
Seiji Eicher authored
Signed-off-by:
Seiji Eicher <seiji@anyscale.com> Co-authored-by:
rongfu.leng <1275177125@qq.com>
-
- 01 Dec, 2025 1 commit
-
-
shivampr authored
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>
-
- 28 Nov, 2025 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 25 Nov, 2025 1 commit
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
- 21 Nov, 2025 1 commit
-
-
wangxiyuan authored
Signed-off-by:wangxiyuan <wangxiyuan1007@gmail.com>
-
- 17 Nov, 2025 1 commit
-
-
Jae-Won Chung authored
The `vllm:kv_cache_usage_perc` Gauge metric is missing `multiprocess_mode="mostrecent"` and ends up returning ``` vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="277"} 0.0 vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="275"} 0.0 vllm:kv_cache_usage_perc{engine="0",model_name="Qwen/Qwen3-VL-8B-Instruct",pid="273"} 0.6530455880475035 ... ``` The deprecated `vllm:gpu_cache_usage_perc` Gauge metric has `multiprocess_mode="mostrecent"`. Signed-off-by:Jae-Won Chung <jwnchung@umich.edu>
-
- 14 Nov, 2025 1 commit
-
-
lyn610 authored
Add tracking and periodic logging for the number of preempted requests in the metrics logger. This helps monitor system behavior under load. Signed-off-by:Yining Liu <610lyn@gmail.com>
-
- 10 Nov, 2025 1 commit
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
- 05 Nov, 2025 1 commit
-
-
Snehlata authored
Signed-off-by:atalhens <sneh.lata@nutanix.com>
-
- 04 Nov, 2025 1 commit
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
- 30 Oct, 2025 1 commit
-
-
Sumanth R Hegde authored
Signed-off-by:SumanthRH <sumanthrh99@gmail.com>
-
- 29 Oct, 2025 2 commits
-
-
Nicolò Lucchesi authored
Signed-off-by:
NickLucche <nlucches@redhat.com> Signed-off-by:
Mark McLoughlin <markmc@redhat.com> Co-authored-by:
Mark McLoughlin <markmc@redhat.com>
-
Braulio Dumba authored
Signed-off-by:Braulio Dumba <Braulio.Dumba@ibm.com>
-
- 24 Oct, 2025 1 commit
-
-
Wentao Ye authored
Signed-off-by:yewentao256 <zhyanwentao@126.com>
-
- 23 Oct, 2025 1 commit
-
-
Tova Movshovitz authored
Signed-off-by:tovam <tovam@pliops.com>
-
- 18 Oct, 2025 1 commit
-
-
Tova Movshovitz authored
Signed-off-by:tovam <tovam@pliops.com>
-
- 14 Oct, 2025 1 commit
-
-
Lucia Fang authored
Signed-off-by:Lu Fang <fanglu@fb.com>
-
- 12 Oct, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
- 10 Oct, 2025 2 commits
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 05 Oct, 2025 2 commits
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
22quinn authored
Signed-off-by:22quinn <33176974+22quinn@users.noreply.github.com>
-
- 03 Oct, 2025 1 commit
-
-
Nicolò Lucchesi authored
Signed-off-by:NickLucche <nlucches@redhat.com>
-
- 27 Sep, 2025 1 commit
-
-
Zhuohan Li authored
Signed-off-by:Zhuohan Li <zhuohan123@gmail.com>
-
- 26 Sep, 2025 1 commit
-
-
Seiji Eicher authored
Signed-off-by:
Seiji Eicher <seiji@anyscale.com> Signed-off-by:
Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by:
Rui Qiao <161574667+ruisearch42@users.noreply.github.com>
-
- 25 Sep, 2025 1 commit
-
-
Zhuohan Li authored
Co-authored-by:
Ye (Charlotte) Qi <yeq@meta.com> Signed-off-by:
Zhuohan Li <zhuohan123@gmail.com>
-
- 24 Sep, 2025 1 commit
-
-
baxingpiaochong authored
Signed-off-by:baxingpiaochong <771405853@qq.com>
-
- 19 Sep, 2025 1 commit
-
-
Nicolò Lucchesi authored
Signed-off-by:NickLucche <nlucches@redhat.com>
-
- 16 Sep, 2025 1 commit
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
- 14 Sep, 2025 1 commit
-
-
wuhang authored
Signed-off-by:
wuhang <wuhang6@huawei.com> Co-authored-by:
Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
-
- 12 Sep, 2025 1 commit
-
-
RichardoMu authored
Signed-off-by:
Mu Huai <tianbowen.tbw@antgroup.com> Signed-off-by:
Ye Zhang <zhysishu@gmail.com> Signed-off-by:
RichardoMu <44485717+RichardoMrMu@users.noreply.github.com> Signed-off-by:
simon-mo <simon.mo@hey.com> Signed-off-by:
Aaron Pham <contact@aarnphm.xyz> Signed-off-by:
22quinn <33176974+22quinn@users.noreply.github.com> Co-authored-by:
Mu Huai <tianbowen.tbw@antgroup.com> Co-authored-by:
Ye Zhang <zhysishu@gmail.com> Co-authored-by:
Benjamin Bartels <benjamin@bartels.dev> Co-authored-by:
simon-mo <simon.mo@hey.com> Co-authored-by:
瑜琮 <ly186375@antfin.com> Co-authored-by:
Aaron Pham <contact@aarnphm.xyz> Co-authored-by:
22quinn <33176974+22quinn@users.noreply.github.com>
-
- 08 Sep, 2025 1 commit
-
-
Chauncey authored
Signed-off-by:
chaunceyjiang <chaunceyjiang@gmail.com> Co-authored-by:
Nick Hill <nhill@redhat.com>
-
- 04 Sep, 2025 1 commit
-
-
Seiji Eicher authored
Signed-off-by:
Seiji Eicher <seiji@anyscale.com> Signed-off-by:
Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by:
Nick Hill <nhill@redhat.com>
-
- 02 Sep, 2025 2 commits
-
-
Mark McLoughlin authored
Signed-off-by:Mark McLoughlin <markmc@redhat.com>
-
Didier Durand authored
Signed-off-by:
Didier Durand <durand.didier@gmail.com> Co-authored-by:
Jee Jee Li <pandaleefree@gmail.com>
-
- 27 Aug, 2025 1 commit
-
-
Hyogeun Oh (오효근) authored
Signed-off-by:
Zerohertz <ohg3417@gmail.com> Signed-off-by:
Hyogeun Oh (오효근) <ohg3417@gmail.com>
-
- 02 Aug, 2025 1 commit
-
-
Nick Hill authored
Signed-off-by:Nick Hill <nhill@redhat.com>
-