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). @ linear_weights_light

AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388)		8 달 전
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 년 전
api_server.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
args.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
embeddings.py	2aec297c55 feat: add embeddings endpoint to openai rest-api server. (#363)	9 달 전
protocol.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	10 달 전
serving_chat.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
serving_completions.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
serving_engine.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전