david/aphrodite-engine

espejo de https://github.com/PygmalionAI/aphrodite-engine

Autor	SHA1 Mensaje	Fecha
AlpinDale	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	hace 5 meses
AlpinDale	6671e3a162 feat: add CPU offloading support (#598)	hace 6 meses
AlpinDale	497bf64942 chore: simplify pipeline parallel code in llama	hace 6 meses
AlpinDale	4599c98f99 feat: dynamic image size support for VLMs	hace 6 meses