llama.cpp

c5aa5e57 - ggml : AVX2 optimization for vec_dot_q4_3_q8_0 and refactoring (#1099)

ggml : AVX2 optimization for vec_dot_q4_3_q8_0 and refactoring (#1099) * AVX2 optimization for vec_dot_q4_3_q8_0 and refactoring * finish AVX vectorization of quantize_row_q8_0 * Rename hsum_int_8 to hsum_i32_8