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).

AlpinDale 05be6085ec core: factor out input preprocessing into a separate class (#1039)		1 week ago
..
__init__.py	62111fab17 feat: allow serving encoder-decoder models in the API server (#664)	4 months ago
data.py	62111fab17 feat: allow serving encoder-decoder models in the API server (#664)	4 months ago
parse.py	05be6085ec core: factor out input preprocessing into a separate class (#1039)	1 week ago
preprocess.py	05be6085ec core: factor out input preprocessing into a separate class (#1039)	1 week ago
registry.py	908ff753a1 fix: phi_3.5_v loading (#896)	3 weeks ago