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). @ b20083a1f3b98b136a950671d8c91e6ea4926c44

Stefan Gligorijevic 0feaa6eba8 Merge branch 'main' into samplers-next		1 year ago
..
openai	048572e4dd Add eta, epsilon, and locally typical sampling	1 year ago
__init__.py	e52de7de70 feat: add API endpoint with FastAPI	1 year ago
api_server.py	d949dd306f add api changes	1 year ago
api_server_ooba.py	124a55a6bf remove repetition penalty alias in ooba api	1 year ago
llm.py	c70abc7522 fix the LLM class for quantization	1 year ago
protocol.py	048572e4dd Add eta, epsilon, and locally typical sampling	1 year ago