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 Commits

79 Ramos

36 Lançamentos

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

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