Rust+OpenCL+AVX2 implementation of LLaMA inference code
Why do you think that https://github.com/oobabooga/text-generation-webui is a good alternative to rllama
Rust+OpenCL+AVX2 implementation of LLaMA inference code
Why do you think that https://github.com/oobabooga/text-generation-webui is a good alternative to rllama