CUDA Library Samples

scalable and robust tree-based speculative decoding algorithm

Fast and memory-efficient exact attention

A universal scalable machine learning model deployment solution

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Demo applications showcasing DJL

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

An Engine-Agnostic Deep Learning Framework in Java

The Java implementation of Dive into Deep Learning (D2L.ai)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

MultiPy is a out of core library for torch.package and torchdeploy.

The LaTeX thesis template provided by the University of Minnesota, with various improvements.