Fixed Cuda Dockerfile
Previously models produced garbage output when running on GPU with layers offloaded. Similar to related fix on another repo: https://github.com/noneabove1182/koboldcpp-docker/commit/331326a0e340ac845855d346f730356b000650c7
P
Pradyumna Singh Rathore committed
d010ea70d20db9064e9c0c73cab36d611d4d35eb
Parent: 66fb034
Committed by GitHub <noreply@github.com>
on 8/10/2023, 3:11:34 PM