A PyTorch native platform for training generative AI models

Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch native quantization and sparsity for training and inference

SGLang is a fast serving framework for large language models and vision language models.

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

A PyTorch Extension

Pytorch domain library for recommendation systems

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Optimized primitives for collective multi-GPU communication

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Continuous builder and binary build scripts for pytorch

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Hydra is a framework for elegantly configuring complex applications

Kria KV260 Vitis platforms and overlays

Splitting Conic Solver

Convolutional Neural Networks

nml is a "simple" matrix/numerical analysis library written in pure C. The scope of the library is to highlight various algorithm implementations related to matrices. Code readability was a major c…

FOSS architecture definitions of FPGA hardware useful for doing PnR device generation.

Verilog to Routing -- Open Source CAD Flow for FPGA Research

Xilinx Run Time for FPGA