ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…

C++ Implementation of PyTorch Tutorials for Everyone

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture

bfloat16 dtype for numpy

C++ package for learning optimal wavelet bases using a neural network approach.

🏆 The winner code for Neurips'23 BigANN Competition OOD and Sparse track.

NYU Projects