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).

18 Ревизии

79 Клонове

36 Версии

AlpinDale a409431c40 feat: draft for cuda kernels		преди 1 година
aphrodite	a409431c40 feat: draft for cuda kernels	преди 1 година
assets	fefbf029c9 revert previous commit	преди 1 година
kernels	a409431c40 feat: draft for cuda kernels	преди 1 година
.gitignore	b6804de3c7 chore: add pycache to gitignore	преди 1 година
LICENSE	fefbf029c9 revert previous commit	преди 1 година
README.md	fefbf029c9 revert previous commit	преди 1 година
requirements.txt	fefbf029c9 revert previous commit	преди 1 година

Aphrodite - The Pygmalion Backend

Work in Progress

Aphrodite is the backend service for PygmalionAI, built on top of FastChat, vLLM, SkyPilot, and more.

Currently a work in progress, not remotely functional.

README.md

Aphrodite - The Pygmalion Backend

Work in Progress