Run LLaMA inference on Apple Silicon GPUs.
Why do you think that https://github.com/OpenGVLab/Multi-Modality-Arena is a good alternative to LLaMA_MPS
Run LLaMA inference on Apple Silicon GPUs.
Why do you think that https://github.com/OpenGVLab/Multi-Modality-Arena is a good alternative to LLaMA_MPS