Mathieu Broillet

Hey mate! I've created an easy docker image to run this UI (and others) really easily with an AMD GPU under Linux. https://github.com/M4TH1EU/ai-suite-rocm/tree/main I haven't been able to make deepspeed...

Someone else also seems to have this issue on Intel GPUs : https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981#discussioncomment-10352096

According to ROCM 6.2.0 release notes, it seems like bitsandbytes is now supported officially ? https://rocm.docs.amd.com/en/latest/about/release-notes.html#memory-savings-for-bitsandbytes-model-quantization Did you just build BnB from their repo and installed it into your SD...

Even with BnB installed I get the same error with the FP8 model, would you mind sharing some more details about how you did it ?

> NF4 I didn't get running, only fp8 (also w.o. BnB) I cannot make the FP8 model run on my setup, I've downloaded this [model](https://huggingface.co/lllyasviel/flux1_dev/blob/main/flux1-dev-fp8.safetensors) from the [Discussion](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981) post. Running...

So after tinkering I managed to get it to work, I think. I built BnB from source using this homemade script [here](https://github.com/M4TH1EU/ai-suite-rocm-local/tree/main/bitsandbytes-rocm-build). I've also included a built wheel of BnB...

I guess we can close this then, the fix is compiling bitsandbytes manually until they merge the multi-backend-refactor branch into the main one. Instructions below : ```bash # Tested on...

After more testing it seems that the Tizen client doesn't support relative paths. works everywhere ```css @import url("https://jellyfin.xxxx.xxx/web/custom/css/test.css"); ``` doesn't work on tizen but works everywhere else : ```css @import...

Hi Frank, Thanks for the fast feedback. I'm unsure about what you mean by "custom/modified" branding? My integration has nothing to do with the official llama.cpp nor Facebook Llama models,...

I see your point, but I really don't think this applies in this case. The goal of this integration is specifically to avoid using OpenAI services but instead allowing the...