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). @ multinode_dynatemp

AlpinDale 46159b107a formatting: pt1		преди 6 месеца
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	преди 1 година
api_server.py	46159b107a formatting: pt1	преди 6 месеца
args.py	8f9cb7235c chore: allow multiple served model names	преди 7 месеца
embeddings.py	2aec297c55 feat: add embeddings endpoint to openai rest-api server. (#363)	преди 9 месеца
protocol.py	a2a24e9b0d feat: list support in message.content (#503)	преди 6 месеца
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	преди 10 месеца
serving_chat.py	46159b107a formatting: pt1	преди 6 месеца
serving_completions.py	8f9cb7235c chore: allow multiple served model names	преди 7 месеца
serving_engine.py	fb7825df8f squash logprobs	преди 7 месеца