A WebGL accelerated JavaScript library for training and deploying ML models.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.

A hardware-accelerated GPU terminal emulator focusing to run in desktops and browsers.

A highly efficient implementation of Gaussian Processes in PyTorch

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Run, compile and execute JavaScript for Scientific Computing and Data Visualization TOTALLY TOTALLY TOTALLY in your BROWSER! An open source scientific computing environment for JavaScript TOTALLY in your browser, matrix operations with GPU acceleration, TeX support, data visualization and symbolic computation.

BlazingSQL is a lightweight, GPU accelerated, SQL engine for Python. Built on RAPIDS cuDF.

A high performance anime upscaler

Deep learning in Rust, with shape checked tensors and neural networks

A new approach to Emacs - Including TypeScript, Threading, Async I/O, and WebRender.

The write-once-run-anywhere GPGPU library for Rust

CUDA Core Compute Libraries

TornadoVM: A practical and efficient heterogeneous programming framework for managed languages

stdgpu: Efficient STL-like Data Structures on the GPU

Cross Platform Professional Procedural Terrain Generation & Texturing Tool

HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

OpenSource GPU, in Verilog, loosely based on RISC-V ISA