david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ 39beed0b87cbbd93bad2b11b939a15941cf67f6f

AlpinDale 39beed0b87 Revert "Refactor AWQ support."		1 yıl önce
..
layers	39beed0b87 Revert "Refactor AWQ support."	1 yıl önce
megatron	39beed0b87 Revert "Refactor AWQ support."	1 yıl önce
models	39beed0b87 Revert "Refactor AWQ support."	1 yıl önce
__init__.py	5e25fe5e64 feat: add model loader	1 yıl önce
hf_downloader.py	39beed0b87 Revert "Refactor AWQ support."	1 yıl önce
loader.py	39beed0b87 Revert "Refactor AWQ support."	1 yıl önce
metadata.py	34295abec4 chore: use xformers attention bias and add docs	1 yıl önce
utils.py	b48fe85378 chore: utilities for modeling	1 yıl önce