GPTQModel
✅ 近期有维护LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
1,284Stars
213Forks
+5近 7 天 Star
Python · 许可证待核验 · 最近推送 2026-10-30
官方仓库与安装文档 ↗Star 历史
2025-09-292026-11-01
查看历史数据
| 日期 | Stars |
|---|---|
| 2026-10-03 | 1,265 |
| 2026-10-04 | 1,266 |
| 2026-10-05 | 1,266 |
| 2026-10-06 | 1,267 |
| 2026-10-07 | 1,267 |
| 2026-10-08 | 1,267 |
| 2026-10-09 | 1,268 |
| 2026-10-10 | 1,268 |
| 2026-10-11 | 1,269 |
| 2026-10-12 | 1,270 |
| 2026-10-13 | 1,270 |
| 2026-10-14 | 1,271 |
| 2026-10-15 | 1,272 |
| 2026-10-16 | 1,272 |
| 2026-10-17 | 1,272 |
| 2026-10-18 | 1,272 |
| 2026-10-19 | 1,273 |
| 2026-10-20 | 1,274 |
| 2026-10-21 | 1,275 |
| 2026-10-22 | 1,277 |
| 2026-10-23 | 1,277 |
| 2026-10-24 | 1,277 |
| 2026-10-25 | 1,278 |
| 2026-10-26 | 1,280 |
| 2026-10-27 | 1,281 |
| 2026-10-28 | 1,281 |
| 2026-10-29 | 1,281 |
| 2026-10-30 | 1,283 |
| 2026-10-31 | 1,283 |
| 2026-11-01 | 1,284 |
获取项目
git clone https://github.com/ModelCloud/GPTQModel.git
相关项目与平替候选
同领域不等于功能完全相同，选型前请核对官方文档和许可证。