llama.cpp

d990e3ff - ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900)

ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900) * ggml : speed-up q4_1 ARM_NEON by ~5% * ggml : implement vaddvq when missing * ggml : implement vminvq and vmaxvq when missing * ggml : implement vzip when missing * ggml : fix comment * ggml : try to use correct ifdef