DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-02-04 10:53:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
stable-diffusion.cpp/docs/performance.md
leejet 8283e1bade enable flash attn by default
2026-01-11 17:35:01 +08:00

281 B
Raw Permalink Blame History

Offload weights to the CPU to save VRAM without reducing generation speed.

Using --offload-to-cpu allows you to offload weights to the CPU, saving VRAM without reducing generation speed.

Use quantization to reduce memory usage.

quantization