Open flatsiedatsie opened 6 months ago
Wllama is a browser-based version of Llama.cpp with low-level capabilities, and has a built-in embedding option too.
https://github.com/ngxson/wllama
While WebLLM only runs on WebGPU-enabled browsers, Wllama can run on all browsers. It could perhaps be a great fallback option? E.g. for Safari / Firefox?
Interesting! Would love to look into it!
Wllama is a browser-based version of Llama.cpp with low-level capabilities, and has a built-in embedding option too.
https://github.com/ngxson/wllama
While WebLLM only runs on WebGPU-enabled browsers, Wllama can run on all browsers. It could perhaps be a great fallback option? E.g. for Safari / Firefox?