CUDA: optimize and refactor MMQ (#8416)
* CUDA: optimize and refactor MMQ * explicit q8_1 memory layouts, add documentation
J
Johannes Gäßler committed
808aba39161e5d7ca2ff24110b5aa14d2e536988
Parent: a977c11
Committed by GitHub <noreply@github.com>
on 7/11/2024, 2:47:47 PM