🚀 Level up your GitHub profile readme with customizable cards including LOC statistics!

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…

distributed-embeddings is a library for building large embedding based models in Tensorflow 2.

Godot Engine – Multi-platform 2D and 3D game engine

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Compatibility tool for Steam Play based on Wine and additional components

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Optimized primitives for collective multi-GPU communication

Vim-fork focused on extensibility and usability

Asynchronous linting and make framework for Neovim/Vim