Production ready LLM model compression/quantization toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
Python · active 2024-06-19 → 2026-08-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 786 days from 2024-06-19 to 2026-08-13. Pushes: 3,936 total, peak 51 in a day. Pull requests: 2,092 total, peak 40 in a day. Issues: 323 total, peak 8 in a day. Comments: 997 total, peak 29 in a day. Stars: 518 total, peak 10 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 |
|---|---|---|---|---|
| Qubitium | 4.3K | 2.1K | 1.3K | 509 |
| CSY-ModelCloud | 1.8K | 1.3K | 397 | 45 |
| ZX-ModelCloud | 367 | 228 | 126 | 7 |
| LRL-ModelCloud | 236 | 157 | 75 | 3 |
| LRL2-ModelCloud | 112 | 80 | 32 | 0 |
| avtc | 105 | 0 | 11 | 82 |
| github-code-quality[bot] | 100 | 0 | 0 | 67 |
| jiqing-feng | 36 | 0 | 16 | 17 |
| PZS-ModelCloud | 33 | 5 | 28 | 0 |
| ZYC-ModelCloud | 28 | 0 | 28 | 0 |
| CL-ModelCloud | 17 | 0 | 16 | 1 |
| wenhuach21 | 16 | 0 | 0 | 10 |
| dependabot[bot] | 16 | 0 | 16 | 0 |
| nbasyl | 12 | 7 | 1 | 3 |
| Xu-Chen | 9 | 0 | 0 | 7 |
| gapsong | 9 | 0 | 0 | 8 |
| xxinine | 9 | 0 | 1 | 3 |
| ywlq | 9 | 0 | 1 | 6 |
| Creling | 8 | 0 | 0 | 7 |
| yuchiwang | 7 | 0 | 1 | 5 |
Recent activity
Latest issues, pull requests and releases
- Pull request#3000Qubitium2026-08-04 18:13
- Issue comment#2926Qubitium2026-06-19 22:18Fix Mllama (Llama3.2-11B-Vision) quantization
- Pull request#2914ZX-ModelCloud2026-05-30 07:27
- Issue comment#2903Qubitium2026-05-21 02:31ParoQuant and GPTAQ Quantization Progress takes too long
- Issue comment#2898Jealousc11gx2026-05-19 06:06[BUG] ParoQuant Quant takes too long, Jit Compilation failed
- Issue comment#2869ZX-ModelCloud2026-05-11 02:33fix: preserve mtp.* tensors for dense Qwen3.5/Qwen3.6 models
- Pull request#2872ZX-ModelCloud2026-05-11 01:22
- Pull request#2870CSY-ModelCloud2026-05-09 02:14
- Issue#2856tp14159265352026-05-06 05:02[BUG] pip install Failed building wheel for pypcre: "unistd.h" : No such file or directory
- Pull request#2847ZX-ModelCloud2026-04-30 02:07
- Pull request#2843ZX-ModelCloud2026-04-29 05:43
- Pull request#2837CSY-ModelCloud2026-04-29 01:33
- Pull request#2836Qubitium2026-04-29 01:10
- Issue comment#2824ZX-ModelCloud2026-04-28 01:16[BUG] Unsupported backend: `gptq_marlin` for `gptq` with format `gptq_v2`
- Pull request#2829CSY-ModelCloud2026-04-27 06:05
- Pull request#2825dblundell2026-04-26 13:48
- Pull request#2823CSY-ModelCloud2026-04-24 09:10
- Pull request#2822ZX-ModelCloud2026-04-24 08:53
- Pull request#2822ZX-ModelCloud2026-04-24 07:08
- Pull request#2821CSY-ModelCloud2026-04-24 03:48
- Pull request#2813CSY-ModelCloud2026-04-23 04:33
- Pull request#2812CSY-ModelCloud2026-04-23 03:44
- Pull request#2809CSY-ModelCloud2026-04-23 03:04
- Pull request#2802CSY-ModelCloud2026-04-22 05:46
- Pull request#2800Qubitium2026-04-21 18:09
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 518 stars here means stars gained during the window, not the repo's star count.