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). @ de62ceb18c50102764d74085eae83163425842f9

AlpinDale de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead		7 months ago
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 months ago
batch_expansion.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	7 months ago
interfaces.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	7 months ago
metrics.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 months ago
multi_step_worker.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	7 months ago
ngram_worker.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
spec_decode_worker.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
top1_proposer.py	e42d0b3455 possibly improve ngram efficiency	7 months ago
util.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	7 months ago