stable-diffusion-webui-docker VS llama.cpp

I also use the Stable Diffusion WebUI Docker, I found it really easy to set up.

I'm currently using this docker setup: https://github.com/AbdBarho/stable-diffusion-webui-docker

I used the Docker install from here. It was easy to get Automatic1111's web interface up and running, but I'm trying to add new models and I can't figure out how to do it.

Docker ftw

I'm using A1111 via https://github.com/AbdBarho/stable-diffusion-webui-docker which was such a perfectly simple way to get set up, and I've been having an absolute blast. Turns out that for the most part I do not even need to leverage the 24GB vram on my 3090.

Yes, Metal seems to allow a maximum of 1/2 of the RAM for one process, and 3/4 of the RAM allocated to the GPU overall. There’s a kernel hack to fix it, but that comes with the usual system integrity caveats. https://github.com/ggerganov/llama.cpp/discussions/2182

For anyone interested in exploring this, llama.cpp has an example implementation here:

https://github.com/ggerganov/llama.cpp/tree/master/examples/...

Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.

well https://github.com/ggerganov/llama.cpp/issues/6849

Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)

Running an embedding server locally is pretty straightforward:

- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases