LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
active 2025-01-05 → 2026-08-01 (UTC)
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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| lvhan028 | 1.7K | 443 | 324 | 484 |
| Copilot | 405 | 2 | 2 | 286 |
| grimoire | 404 | 2 | 76 | 148 |
| RunningLeon | 241 | 1 | 26 | 91 |
| CUHKSZzxy | 222 | 0 | 42 | 100 |
| github-actions[bot] | 221 | 0 | 0 | 145 |
| windreamer | 203 | 7 | 35 | 102 |
| irexyc | 159 | 3 | 20 | 71 |
| jinminxi104 | 89 | 0 | 12 | 50 |
| lzhangzz | 87 | 0 | 17 | 38 |
| AllentDan | 70 | 0 | 9 | 36 |
| zhulinJulia24 | 69 | 6 | 15 | 20 |
| ywx217 | 34 | 0 | 1 | 18 |
| yao-fengchen | 22 | 0 | 8 | 11 |
| JackWeiw | 21 | 0 | 9 | 8 |
| Tsundoku958 | 21 | 0 | 2 | 13 |
| SHshenhao | 20 | 0 | 0 | 10 |
| JimyMa | 18 | 0 | 8 | 5 |
| zhaochaoxing | 17 | 0 | 9 | 4 |
| shell-nlp | 16 | 0 | 0 | 8 |
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 02:07feat(turbomind): support priority schedule policy
- Issue comment#4614windreamer2026-05-29 02:06feat(turbomind): support priority schedule policy
- Pull request#4633lvhan0282026-05-28 07:18
- Issue comment#4606lvhan0282026-05-24 03:34TEST: 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 07:47Fix health latency under concurrent VL request preparation
- Issue comment#4570lvhan0282026-05-09 05:47Fix 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 21:14KV 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.