cturan/llama.cpp

mirror de https://github.com/cturan/llama.cpp

Autor	SHA1 Mensagem	Data
Alfred	ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)	há 4 semanas atrás
Max Krasnyansky	63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)	há 2 meses atrás