GitHub - turboderp/exllamav2: A fast inference library for running LLMs locally on modern consumer-class GPUs

GitHub - turboderp/exllamav2: A fast inference library for running LLMs locally on modern consumer-class GPUs

turboderpgithub.com
Thumbnail of GitHub - turboderp/exllamav2: A fast inference library for running LLMs locally on modern consumer-class GPUs
Ahmadx.com

okuvshynov GitHub - okuvshynov/slowllama: Finetune llama2-70b and codellama on MacBook Air without quantization

google GitHub - google/maxtext: A simple, performant and scalable Jax LLM!