david/aphrodite-engine

miroir de https://github.com/PygmalionAI/aphrodite-engine

Auteur	SHA1 Message	Date
AlpinDale	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	il y a 8 mois
AlpinDale	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	il y a 8 mois
AlpinDale	50b7c13db0 refactor: attention selector (#552)	il y a 8 mois
AlpinDale	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	il y a 8 mois