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).

33 커밋

79 브랜치

36 릴리즈

AlpinDale 28866137ea feat: add swiglu activation		1 년 전
aphrodite	b48fe85378 chore: utilities for modeling	1 년 전
assets	fefbf029c9 revert previous commit	1 년 전
kernels	28866137ea feat: add swiglu activation	1 년 전
.gitignore	3c3944153c feat: add generic attention and FP32 dtype kernels	1 년 전
LICENSE	fefbf029c9 revert previous commit	1 년 전
README.md	fefbf029c9 revert previous commit	1 년 전
requirements.txt	fefbf029c9 revert previous commit	1 년 전

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