Is this similar to fastllm?
https://github.com/ztxz16/fastllm
fastllm targets the GPU, while colibri uses CPU inference only
I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti...
fastllm targets the GPU, while colibri uses CPU inference only
I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti...