upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-23 11:20:53 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
default_flash_attn
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

Reference in New Issue View Git Blame Copy Permalink