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 Achegas

79 Branches

36 Lanzamentos

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

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