Skip to content

perf(moss): reduce CUDA Q8 inference overhead while preserving output pixels - #2201

Closed
mirek190 wants to merge 2 commits into
leejet:masterfrom
mirek190:perf/moss-q8-exact-cuda
Closed

perf(moss): reduce CUDA Q8 inference overhead while preserving output pixels#2201
mirek190 wants to merge 2 commits into
leejet:masterfrom
mirek190:perf/moss-q8-exact-cuda

fix(moss): guard optional SiTU support with older ggml

ef690a2
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs