GodEmperor785

[Bug]: Multidiffusion integrated + controlnet integrated errors

4

### Checklist - [ ] The issue exists after disabling all extensions - [X] The issue exists on a clean installation of webui - [X] The issue is caused by...

Add Q4/Q8 cache for llama.cpp

4

**Description** For some time there is an option to use Q8 and Q4 KV cache in llama.cpp. It is present for example in KoboldCPP and works great there. Using quantized...

llama.cpp sampling doesn't work in 1.15

2

### Describe the bug llama.cpp models always gives exactly the same output (compared in winmerge to be sure), like they ignore any sampling options and seed. Sometimes the first output...

### Feature Idea A follow up to #227 - as requested, new issue is made. "diffusion_models" is still not configurable and trying to load Flux model from anywhere else than...