A high-throughput and memory-efficient inference and serving engine for LLMs
active 2025-03-25 → 2026-08-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 504 days from 2025-03-25 to 2026-08-10. Pushes: 2,519 total, peak 21 in a day. Pull requests: 263 total, peak 8 in a day. Issues: 26 total, peak 2 in a day. Comments: 247 total, peak 9 in a day. Stars: 25 total, peak 1 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 |
|---|---|---|---|---|
| AndreasKaratzas | 558 | 555 | 3 | 0 |
| gshtras | 237 | 178 | 36 | 11 |
| Rohan138 | 184 | 168 | 4 | 6 |
| tjtanaavllm | 148 | 110 | 25 | 8 |
| mgehre-amd | 141 | 126 | 5 | 6 |
| github-actions[bot] | 132 | 0 | 19 | 104 |
| dllehr-amd | 130 | 76 | 30 | 5 |
| charlifu | 116 | 113 | 2 | 0 |
| ganyi1996ppo | 113 | 111 | 1 | 1 |
| maleksan85 | 102 | 78 | 7 | 8 |
| micah-wil | 93 | 93 | 0 | 0 |
| zejunchen-zejun | 85 | 63 | 8 | 8 |
| fsx950223 | 84 | 75 | 9 | 0 |
| wuhuikx | 76 | 48 | 6 | 11 |
| gyohuangxin | 76 | 74 | 2 | 0 |
| mawong-amd | 62 | 62 | 0 | 0 |
| k50112113 | 55 | 42 | 11 | 1 |
| xytpai | 41 | 32 | 4 | 5 |
| roberteg16 | 39 | 33 | 1 | 2 |
| liangliangchang | 36 | 36 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#1030eble-amd2026-06-26 20:01
- Pull request#1015roberteg162026-06-22 17:41
- Pull request#985mgehre-amd2026-06-15 22:44
- Pull request#988JadenMathias2026-06-05 22:26
- Issue comment#886eble-amd2026-05-29 21:23Improve int4 AWQ GEMV performance on Radeon 8060S and similar GPUs
- Issue comment#926harkgill-amd2026-05-25 15:42[Bug]: use vllm images deployed deepseek-v4 report error
- Issue comment#959roberteg162026-05-20 21:06Revert "wvSplitK gfx11 K=2048 N=1: tune to (W=32, AC=16, UN=8)"
- Issue#927harkgill-amd2026-05-12 13:27[Bug]: 使用aisbench测试qwen3.5报异常
- Pull request#915gshtras2026-04-30 15:28
- Issue comment#906github-actions[bot]2026-04-27 19:13Rogarcia.make grid equal to cu count
- Issue comment#892mgehre-amd2026-04-27 09:07[Bugfix][ROCm] Fix _validate_layer_invariants rejection
- Pull request#901ChuanLi11012026-04-27 04:40
- Pull request#900tjtanaavllm2026-04-26 08:44
- Pull request#899tjtanaa2026-04-25 05:57
- Pull request#893mgehre-amd2026-04-24 07:07
- Issue comment#847github-actions[bot]2026-04-22 02:14optimized dsv3.2 missing underscore
- Pull request#887amd-callumm2026-04-21 21:41
- Pull request#882mgehre-amd2026-04-20 22:14
- Issue#696github-actions[bot]2026-04-19 02:15[Bug]: Mixed GPTQ quant not working with gfx1100,gfx1201 - Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix
- Issue comment#696github-actions[bot]2026-04-19 02:15[Bug]: Mixed GPTQ quant not working with gfx1100,gfx1201 - Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix
- Issue#861vagabond25222026-04-18 18:23[Installation]:
- Pull request#879mgehre-amd2026-04-15 10:48
- Pull request#878mgehre-amd2026-04-15 10:47
- Issue comment#816github-actions[bot]2026-04-03 02:14[ROCm][FP4 BMM] integrate FP4 BMM
- Issue comment#851github-actions[bot]2026-04-03 02:14[Triton] fix rope kv_cache for RocmAiterUnifiedAttentionImpl + v.contiguous() remove
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 25 stars here means stars gained during the window, not the repo's star count.