Comment by vikmals 2 days ago fastllm targets the GPU, while colibri uses CPU inference only 1 comment vikmals Reply aliljet 2 days ago I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti...
aliljet 2 days ago I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti...
I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti...