Introduction of gemm4xN and gemmMx4 for Q4_0 and Q8_0 for better performance results#8908

ggerganov merged 1 commit intoggml-org:masterggml-org/llama.cpp:masterfrom

Srihari-mcw:q8_0_q4_0_fp16_delta_multiply_parallelSrihari-mcw/llama.cpp:q8_0_q4_0_fp16_delta_multiply_parallelCopy head branch name to clipboard