ztxz16/fastllm
fastllm是后端无依赖的高性能大模型推理库,帮助您在大部分设备上高效推理大模型!
3 best points · 0 comments · 1 Hacker News post · 5,131 GitHub stars · View on GitHub
Hacker News discussions
- Fastllm: A LLM inference library that runs DeepSeek-V4 with 10GB VRAM (3 points, 0 comments, by nogajun, 2026-06-30)