
Rank #3,148 2,404 starsPython
club-3090
by noonghunna (personal account)
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. (description from the project’s GitHub page)
Repository facts
- Stars
- 2,404
- Forks
- 165
- Open issues and pull requests
- 72
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- noonghunna · Personal account
- Created
- Apr 28, 2026
- Last push
- Oct 18, 2026