Skip to content

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

active 2025-01-052026-08-01 (UTC)

Partial coverage12,275 / 13,981 hourly files (88%) · 2 absent upstream · 1,701 failed, retryable2025-01-052026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
6.5K
Pushes
471
Pull requests
690
Issues
505
Stars
1.3K
Forks
113

Activity over time

Daily event counts in the loaded window

Line chart, 574 days from 2025-01-05 to 2026-08-01. Pushes: 471 total, peak 7 in a day. Pull requests: 690 total, peak 10 in a day. Issues: 505 total, peak 7 in a day. Comments: 2,201 total, peak 24 in a day. Stars: 1,281 total, peak 19 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
lvhan0281.7K443324484
Copilot40522286
grimoire404276148
RunningLeon24112691
CUHKSZzxy222042100
github-actions[bot]22100145
windreamer203735102
irexyc15932071
jinminxi1048901250
lzhangzz8701738
AllentDan700936
zhulinJulia246961520
ywx217340118
yao-fengchen220811
JackWeiw21098
Tsundoku958210213
SHshenhao200010
JimyMa18085
zhaochaoxing17094
shell-nlp16008

Recent activity

Latest issues, pull requests and releases

  • Pull request#4711lvhan0282026-06-30 03:09
  • Pull request#4702lvhan0282026-06-25 02:58
  • Issue comment#4527joebnb2026-06-10 08:30
    [Feature] Support MiniMax-M2.7 in TurboMind engine
  • Pull request#4661RunningLeon2026-06-09 07:56
  • Issue comment#4614windreamer2026-05-29 02:07
    feat(turbomind): support priority schedule policy
  • Issue comment#4614windreamer2026-05-29 02:06
    feat(turbomind): support priority schedule policy
  • Pull request#4633lvhan0282026-05-28 07:18
  • Issue comment#4606lvhan0282026-05-24 03:34
    TEST: update video test
  • Pull request#4616lvhan0282026-05-23 11:29
  • Pull request#4572RunningLeon2026-05-11 06:42
  • Pull request#4572lvhan0282026-05-11 06:38
  • Issue comment#4570CUHKSZzxy2026-05-09 07:47
    Fix health latency under concurrent VL request preparation
  • Issue comment#4570lvhan0282026-05-09 05:47
    Fix health latency under concurrent VL request preparation
  • Pull request#4576lvhan0282026-05-09 04:23
  • Pull request#4576lvhan0282026-05-09 04:23
  • Pull request#4574lvhan0282026-05-09 01:57
  • Issue#4507jagmarques2026-05-08 21:14
    KV cache compression for longer context support
  • Issue#4567lvhan0282026-05-06 04:58
    [Bug] requirements for the version of torch and triton
  • Pull request#4550lvhan0282026-04-28 03:19
  • Pull request#4548lvhan0282026-04-26 03:55
  • Issue comment#4553ZhijunLStudio2026-04-25 08:00
    [Feature] TurboMind backend missing VLM support for DeepSeek-VL2, Llama4, Gemma3, Qwen3-VL
  • Issue comment#4553lvhan0282026-04-25 06:22
    [Feature] TurboMind backend missing VLM support for DeepSeek-VL2, Llama4, Gemma3, Qwen3-VL
  • Pull request#4541grimoire2026-04-25 06:08
  • Pull request#4545lvhan0282026-04-22 05:46
  • Pull request#4543ZhijunLStudio2026-04-22 04:15

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,281 stars here means stars gained during the window, not the repo's star count.