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 6b9561ef07 adapt TGI incremental detokenization		il y a 1 an
..
openai	7a85354b69 add logits back	il y a 1 an
__init__.py	e52de7de70 feat: add API endpoint with FastAPI	il y a 1 an
api_server.py	d949dd306f add api changes	il y a 1 an
api_server_alt.py	d949dd306f add api changes	il y a 1 an
llm.py	6b9561ef07 adapt TGI incremental detokenization	il y a 1 an
protocol.py	d949dd306f add api changes	il y a 1 an