Startseite Erkunden Hilfe
Registrieren Anmelden
david
/
aphrodite-engine
Mirror von https://github.com/PygmalionAI/aphrodite-engine
1
0
Fork 0
Dateien Issues 0 Wiki

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).

Struktur: 28866137ea
Branches Tags
aphrodite-engin...
ZIP TAR.GZ
AlpinDale 28866137ea feat: add swiglu activation vor 1 Jahr
aphrodite b48fe85378 chore: utilities for modeling vor 1 Jahr
assets fefbf029c9 revert previous commit vor 1 Jahr
kernels 28866137ea feat: add swiglu activation vor 1 Jahr
.gitignore 3c3944153c feat: add generic attention and FP32 dtype kernels vor 1 Jahr
LICENSE fefbf029c9 revert previous commit vor 1 Jahr
README.md fefbf029c9 revert previous commit vor 1 Jahr
requirements.txt fefbf029c9 revert previous commit vor 1 Jahr

README.md

Aphrodite - The Pygmalion Backend

Work in Progress

aphrodite

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

Currently a work in progress, not remotely functional.