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). @ bitnet

AlpinDale 696f2cd59c add phi3_small support with blocksparse attention		vor 6 Monaten
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	vor 1 Jahr
api_server.py	fe431bb840 check for next port if current is unavailable	vor 6 Monaten
args.py	8f9cb7235c chore: allow multiple served model names	vor 8 Monaten
protocol.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	vor 6 Monaten
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	vor 11 Monaten
serving_chat.py	e8b7f53321 allow prompt token IDs in the logits processor api	vor 6 Monaten
serving_completions.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	vor 6 Monaten
serving_embedding.py	54a4cef647 add bias and tie word embedding support for llama	vor 6 Monaten
serving_engine.py	696f2cd59c add phi3_small support with blocksparse attention	vor 6 Monaten