CUDA: Fixed OpenLLaMA 3b mmq, reduced compile time (#2590)
J
Johannes Gäßler committed
f64d44a9b9581cd58f7ec40f4fa1c3ca5ca18e1e
Parent: b19edd5
Committed by GitHub <noreply@github.com>
on 8/12/2023, 10:24:45 PM