noonghunna/club-3090

club-3090

✅ 近期有维护

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.

2,473Stars
169Forks
+25近 7 天 Star

Python · Apache-2.0 · 最近推送 2026-11-03

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

2026-04-272026-11-03
查看历史数据
日期Stars
2026-10-052,346
2026-10-062,350
2026-10-072,352
2026-10-082,355
2026-10-092,358
2026-10-102,364
2026-10-112,373
2026-10-122,378
2026-10-132,386
2026-10-142,393
2026-10-152,397
2026-10-162,399
2026-10-172,399
2026-10-182,403
2026-10-192,411
2026-10-202,417
2026-10-212,425
2026-10-222,433
2026-10-232,436
2026-10-242,440
2026-10-252,443
2026-10-262,447
2026-10-272,451
2026-10-282,454
2026-10-292,458
2026-10-302,462
2026-10-312,467
2026-11-012,470
2026-11-022,472
2026-11-032,473

获取项目

git clone https://github.com/noonghunna/club-3090.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。