noonghunna/club-3090

Python

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.

59/ 100

Activity

Stable

Score Breakdown

25
Issue Response
/ 25 pts
20
PR Merge Rate
/ 20 pts
0
External Contributions
/ 15 pts
8
Commit Distribution
/ 15 pts
0
Good First Issues
/ 10 pts
2
Complexity
/ 10 pts
4
CONTRIBUTING
/ 4 pts
0
Code of Conduct
/ 1 pts
0
No Penalty
Repo is code
0
No Penalty
Repo is active

Repository Stats

Stars
2.5k
Forks
169
Open Issues
99
Lines of Code
372.6k
Contributors
41

Contributor Friendliness

Good First Issues
0
Help Wanted
0
Avg Issue Response
2h
Avg PR Merge Time
1h
Avg PR Review Time
2h
Issue Close Rate
42%

Project Info

Created
Apr 28, 2026
Age
6 months old
Last Push
Today
Size
60.1 MB