Comment by nogajun 2 days ago Is this similar to fastllm?https://github.com/ztxz16/fastllm 2 comments nogajun Reply vikmals 2 days ago fastllm targets the GPU, while colibri uses CPU inference only 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...
vikmals 2 days ago fastllm targets the GPU, while colibri uses CPU inference only 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...
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...