llama.cpp

8ab8ba62 - llama : prevent usage of k-quants when tensor size is not a multiple of 256 (#1921)

llama : prevent usage of k-quants when tensor size is not a multiple of 256 (#1921) * Fix examples/metal * k-quants: prevent usage when tensor size is not divisible by 256 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>