sycl : port multi-column MMVQ from CUDA backend (~45% speculative decoding speedup on Intel Arc)#21845

ggerganov merged 1 commit into

ggml-org:masterggml-org/llama.cpp:masterfrom

masonmilby:sycl-mmvq-multicolmasonmilby/llama.cpp:sycl-mmvq-multicolCopy head branch name to clipboard