cturan/llama.cpp

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

작성자	SHA1 메시지	날짜
Alfred	ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)	1 개월 전
Max Krasnyansky	63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)	3 달 전