cturan/llama.cpp

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

Autor	SHA1 Mensagem	Data
snadampal	a07d0fee1f ggml : add mmla kernels for quantized GEMM (#4966)	1 ano atrás
Cebtenzzre	bc39553c90 build : enable more non-default compiler warnings (#3200)	2 anos atrás
Stephan Walter	1b107b8550 ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)	2 anos atrás
Kawrakow	1bfc153e2f ggml : a faster version for Q4_1 x Q8_0 dot products (#1083)	2 anos atrás