Rust+OpenCL+AVX2 implementation of LLaMA inference code
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
shenjackyuanjie opened this issue a year ago · comments
I try to load llama2-7b but it dose not work
My GPU is a RX 550, so I can not run any CUDA stuf rllama is the only way to experience llm on my local machine
well, actually, I find this