New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

🚀 Introducing an efficient decoding method tailerd for next-scale prediction. 🚀 Faster and less memory consumption #93

Open

czg1225 opened this issue Nov 28, 2024 · 1 comment

czg1225 commented Nov 28, 2024

Thanks a lot to VAR's wonderful work! We introduce Collaborative Decoding(CoDe), an efficient decoding strategy tailored for Visual Auto-Regressive Modeling. It offers a 1.7x speedup and 0.5x Memory with only a negligible impact on quality.
Paper https://arxiv.org/pdf/2411.17787
GitHub: https://github.com/czg1225/CoDe
Project Page: https://czg1225.github.io/CoDe_page/

Contributor

iFighting commented Nov 29, 2024

Thanks a lot to VAR's wonderful work! We introduce Collaborative Decoding(CoDe), an efficient decoding strategy tailored for Visual Auto-Regressive Modeling. It offers a 1.7x speedup and 0.5x Memory with only a negligible impact on quality. Paper https://arxiv.org/pdf/2411.17787 GitHub: https://github.com/czg1225/CoDe Project Page: https://czg1225.github.io/CoDe_page/

@czg1225 Thanks for your nice work, i will read this paper today

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment