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). @ 737f1c3351c3d3824617efcc95550449e6a5fe18

AlpinDale 46159b107a formatting: pt1		пре 7 месеци
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	пре 1 година
api_server.py	46159b107a formatting: pt1	пре 7 месеци
args.py	8f9cb7235c chore: allow multiple served model names	пре 8 месеци
embeddings.py	2aec297c55 feat: add embeddings endpoint to openai rest-api server. (#363)	пре 10 месеци
protocol.py	a2a24e9b0d feat: list support in message.content (#503)	пре 7 месеци
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	пре 11 месеци
serving_chat.py	46159b107a formatting: pt1	пре 7 месеци
serving_completions.py	8f9cb7235c chore: allow multiple served model names	пре 8 месеци
serving_engine.py	fb7825df8f squash logprobs	пре 8 месеци