mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-29 07:34:31 +00:00
32 lines
1.1 KiB
TeX
32 lines
1.1 KiB
TeX
\section{Conclusion}
|
|
|
|
|
|
Hanzo ML provides a Rust-native ML framework optimized for deployment and privacy-preserving computation. The combination of small binary size, SIMD-optimized kernels, and FHE-compatible layers enables new deployment scenarios impossible with traditional frameworks. We release the framework as open source to advance privacy-preserving AI.
|
|
|
|
\bibliographystyle{plain}
|
|
\begin{thebibliography}{10}
|
|
|
|
\bibitem{tchrs2020}
|
|
L. Mazare. tch-rs: Rust bindings for PyTorch. 2020.
|
|
|
|
\bibitem{burn2023}
|
|
N. Laustsen. Burn: A flexible deep learning framework. 2023.
|
|
|
|
\bibitem{tfhe2016}
|
|
I. Chillotti et al. TFHE: Fast Fully Homomorphic Encryption over the Torus. ASIACRYPT, 2016.
|
|
|
|
\bibitem{ckks2017}
|
|
J. H. Cheon et al. Homomorphic Encryption for Arithmetic of Approximate Numbers. ASIACRYPT, 2017.
|
|
|
|
\bibitem{ggml2023}
|
|
G. Gerganov. ggml: Tensor library for machine learning. 2023.
|
|
|
|
\bibitem{candle2023}
|
|
HuggingFace. Candle: Minimalist ML framework for Rust. 2023.
|
|
|
|
\bibitem{safetensors2022}
|
|
N. Patry. Safetensors: Simple, safe tensor serialization. 2022.
|
|
|
|
\end{thebibliography}
|
|
|