cturan/llama.cpp

의 미러 https://github.com/cturan/llama.cpp

작성자	SHA1 메시지	날짜
Johannes Gäßler	e81b8e4b7f llama: use FA + max. GPU layers by default (#15434)	4 달 전
Aman Gupta	8a4a856277 Add LLaDA 8b Diffusion model (#14771)	5 달 전
Aman Gupta	ab14019821 Support diffusion models: Add Dream 7B (#14644)	6 달 전