llama.cpp

c67cc983 - ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)

ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227) * Add SVE support for q4_K_q8_K * Update ggml/src/ggml-cpu/ggml-cpu-quants.c change to use K_SCALE_SIZE Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>