ThreeJawedChuckDon't overlook llama.cpp's rpc-server feature.
It loads the rpc machine’s part of the model across the network every time you start the server,
I have to correct myself. It appears newer versions of rpc-server have a cache option and you can point them to a locally stored version of the model to avoid the network cost.
What’s the advantage over Ollama? I’ve tried a few different combinations of Nvidia cards and each time, they all got used to their full potential (it seemed)
What’s the advantage over Ollama?
I’m very new to this so someone more knowledgeable should probably answer this for real.
My impression was that ollama somehow uses the llama.cpp source internally, but wraps it up to provide features like auto-downloading of models. I didn’t care about that, but I liked the very tiny dependency footprint of llama.cpp. I haven’t tried ollama for network inference.
There are other backends too which support network inference, and some posts allege they are better for that than llama.cpp is. vllm and … exllama or something like that? I haven’t looked into either of them. I’m running on inertia so far with llama.cpp, since it was so easy to get going and I’m kinda lazy.
That’s a pretty good summation unless you want a more technical breakdown like how it handles weights, or how it runs connectors for multi node setups.
Check out mozillas project for LLMs. It’s a nice halfway point between llama.cpp and openwebui.
To add to my lame noob answer, I found this, which has a better rundown of ollama vs llama.cpp. I don’t know if it’s considered bad form to link to ##ddit on lemmy, so I’ll just put the title here and you can search for it on there if you want. There are a couple informative posts which are upvoted. “There is a big difference between use LM-Studio, Ollama, LLama.cpp?”
Feel free to link anything you think is relevant.