weicj/vLLM-2080Ti-Definitive

vLLM-2080Ti-Definitive

✅ 近期有维护

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://discord.gg/VFqVVySdMS )

1,200Stars
167Forks
+14近 7 天 Star

Python · Apache-2.0 · 最近推送 2026-10-01

官方仓库与安装文档 ↗

GitValue · 价值证据

待补证 · 证据覆盖 0%

试跑评分;文档声明与实测分开。未收集证据不代表项目没有价值。

Star 历史

2026-06-012026-11-02
查看历史数据
日期Stars
2026-10-041,084
2026-10-051,090
2026-10-061,098
2026-10-071,102
2026-10-081,109
2026-10-091,113
2026-10-101,118
2026-10-111,124
2026-10-121,131
2026-10-131,135
2026-10-141,140
2026-10-151,148
2026-10-161,153
2026-10-171,156
2026-10-181,159
2026-10-191,163
2026-10-201,168
2026-10-211,171
2026-10-221,172
2026-10-231,175
2026-10-241,179
2026-10-251,182
2026-10-261,185
2026-10-271,187
2026-10-281,189
2026-10-291,192
2026-10-301,194
2026-10-311,195
2026-11-011,195
2026-11-021,200

获取项目

git clone https://github.com/weicj/vLLM-2080Ti-Definitive.git

克隆仅获取源码;依赖与安装步骤请参照项目的 README.

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。