Commits · 9e6bcda3ac13b97ea620155c8dc98ca434cdb234 · OpenDAS / vllm_cscc

28 Nov, 2025 1 commit
- [mypy] Enable type checking for more directories (#29674) · 9e6bcda3
  Cyrus Leung authored Nov 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9e6bcda3
25 Nov, 2025 1 commit
- [Metrics] Scheduled removal of deprecated metrics (#29330) · 9cf4edae
  Mark McLoughlin authored Nov 25, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  9cf4edae
21 Nov, 2025 1 commit
- [Doc] Update plugin doc (#28532) · 4050bae4
  wangxiyuan authored Nov 21, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  4050bae4
17 Nov, 2025 1 commit

[Metrics] Fix KV cache usage percent metric multiproc (#28792) · d4acf518

Jae-Won Chung authored Nov 17, 2025



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>

d4acf518

14 Nov, 2025 1 commit

[Metrics] Log number of preempted requests (#28522) · ecf8230d

lyn610 authored Nov 14, 2025

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>

ecf8230d

10 Nov, 2025 1 commit
- [Metrics] Refactor LoRA state tracking (#26801) · 6f7de33b
  Mark McLoughlin authored Nov 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  6f7de33b
05 Nov, 2025 1 commit
- [Feature]: Add corrupted request metric to V1 metrics system. (#27306) · e1560178
  Snehlata authored Nov 06, 2025
```
Signed-off-by: atalhens <sneh.lata@nutanix.com>
```
  e1560178
04 Nov, 2025 1 commit
- [Metrics] Enable sleep state metric outside of dev mode (#27867) · 380ba681
  Mark McLoughlin authored Nov 04, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  380ba681
30 Oct, 2025 1 commit
- [Fix] Skip `record_sleep_state` logic in `PrometheusStatsLogger` if not in dev mode (#27789) · 49170025
  Sumanth R Hegde authored Oct 30, 2025
```
Signed-off-by: SumanthRH <sumanthrh99@gmail.com>
```
  49170025
29 Oct, 2025 2 commits
- [KVConnector] Add metrics to Prometheus-Grafana dashboard (#26811) · accb8fab
  Nicolò Lucchesi authored Oct 29, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  accb8fab
- [Core] Exposing engine sleep & wake_up state as prometheus metrics (#24176) · 1da3309a
  Braulio Dumba authored Oct 29, 2025
```
Signed-off-by: Braulio Dumba <Braulio.Dumba@ibm.com>
```
  1da3309a
24 Oct, 2025 1 commit
- [Log] Optimize Startup Log (#26740) · 52efc34e
  Wentao Ye authored Oct 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  52efc34e
23 Oct, 2025 1 commit
- [Metrics] [KVConnector] Add connector prefix cache hit rate stats (#26245) · 88afa110
  Tova Movshovitz authored Oct 23, 2025
```
Signed-off-by: tovam <tovam@pliops.com>
```
  88afa110
18 Oct, 2025 1 commit
- [V1][Metrics][Plugin] Add plugin support for custom `StatLoggerBase` implementations (#22456) · 83e760c5
  Tova Movshovitz authored Oct 19, 2025
```
Signed-off-by: tovam <tovam@pliops.com>
```
  83e760c5
14 Oct, 2025 1 commit
- [Misc][DP] support customized aggregated logger for dp (#24354) · 8317f723
  Lucia Fang authored Oct 13, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
  8317f723
12 Oct, 2025 1 commit
- Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
  Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8fcaaf6a
10 Oct, 2025 2 commits
- [Metrics] Add test for multi-modal cache stats logging (#26588) · e5192819
  Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  e5192819
- [Metrics] Log multi-modal cache stats and fix reset (#26285) · ad430a67
  Cyrus Leung authored Oct 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ad430a67
05 Oct, 2025 1 commit
- Convert formatting to use `ruff` instead of `yapf` + `isort` (#26247) · d6953beb
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6953beb
03 Oct, 2025 1 commit
- [NIXL][Misc] Expose metrics from NIXL for logging to CLI (#25388) · 48f30902
  Nicolò Lucchesi authored Oct 03, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  48f30902
25 Sep, 2025 1 commit
- [Core] Enable command line logging for LLMEngine (#25610) · 8c435c9b
  Zhuohan Li authored Sep 25, 2025
```
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
```
  8c435c9b
24 Sep, 2025 1 commit
- [V1][Metrics] Add per-request TPOT histogram (#24015) · d06b5a95
  baxingpiaochong authored Sep 24, 2025
```
Signed-off-by: baxingpiaochong <771405853@qq.com>
```
  d06b5a95
19 Sep, 2025 1 commit
- [P/D][Nixl] Introduce `KVTransferMetrics` and aggregation strategy (#22188) · a3d087ad
  Nicolò Lucchesi authored Sep 19, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  a3d087ad
16 Sep, 2025 1 commit
- [Metrics] Hide deprecated metrics with gpu_ prefix (#24245) · 2942970d
  Mark McLoughlin authored Sep 16, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  2942970d
14 Sep, 2025 1 commit

[Spec Decoding]Support Spec Decoding Metrics in DP Mode (#24049) · 90f3f7d7

wuhang authored Sep 15, 2025


Signed-off-by: wuhang <wuhang6@huawei.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

90f3f7d7

08 Sep, 2025 1 commit
- [Bugfix] Disable the statslogger if the api_server_count is greater than 1 (#22227) · e680723e
  Chauncey authored Sep 09, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  e680723e
04 Sep, 2025 1 commit

[Misc] Have AsyncLLM `custom_stat_loggers` extend default logger list (#20952) · 60b755cb

Seiji Eicher authored Sep 04, 2025


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>

60b755cb

02 Sep, 2025 1 commit
- [Metrics] Deprecate TPOT in favor of ITL (#24110) · 24177984
  Mark McLoughlin authored Sep 02, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  24177984
27 Jul, 2025 1 commit
- Refactor: Remove numpy dependency from LoggingStatLogger (#20529) · a8936e51
  ZiTian.Zhao authored Jul 27, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  a8936e51
21 Jul, 2025 1 commit

[DP] Fix Prometheus Logging (#21257) · 29d1ffc5

Robert Shaw authored Jul 21, 2025


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

29d1ffc5

19 Jun, 2025 1 commit

Support embedding models in V1 (#16188) · 799397ee

Maximilien de Bayser authored Jun 19, 2025


Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>

799397ee

14 Jun, 2025 1 commit
- [V1][Metrics] Deprecate metrics with gpu_ prefix for non GPU specific metrics. (#18354) · d1e34cc9
  Saheli Bhattacharjee authored Jun 14, 2025
```
Signed-off-by: Saheli Bhattacharjee <saheli@krai.ai>
```
  d1e34cc9
03 Jun, 2025 1 commit
- [Misc] Add SPDX-FileCopyrightText (#19100) · 02f0c7b2
  Simon Mo authored Jun 03, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  02f0c7b2
30 May, 2025 1 commit
- [Perf] API-server scaleout with many-to-many server-engine comms (#17546) · 2dbe8c07
  Nick Hill authored May 30, 2025
  
  2dbe8c07
27 May, 2025 1 commit
- [V1][Metrics] Add API for accessing in-memory Prometheus metrics (#17010) · 06a03380
  Mark McLoughlin authored May 27, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  06a03380
16 May, 2025 1 commit
- [Misc] Add Ray Prometheus logger to V1 (#17925) · 54181767
  Seiji Eicher authored May 16, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  54181767
12 May, 2025 1 commit
- [v1][KVCacheManager] Change prefix caching metric from counting blocks to counting tokens (#18003) · 302f3aca
  Chen Zhang authored May 13, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  302f3aca
10 May, 2025 1 commit
- [V1][Spec Decoding] Log accumulated metrics after system goes idle (#17913) · 7042cc96
  Mark McLoughlin authored May 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  7042cc96
30 Apr, 2025 1 commit
- [V1][Bugfix]: vllm v1 verison metric num_gpu_blocks is None (#15755) · d8037867
  rongfu.leng authored Apr 30, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  d8037867
27 Apr, 2025 1 commit
- [Metrics] Fix minor inconsistencies in bucket progression (#17262) · 4213475e
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4213475e