Explore Projects
Discover 62 open source projects
Showing 21-40 of 62 projects
turboderp-org/exllamav2
A fast inference library for running large language models (LLMs) locally on modern GPUs
openxla/xla
A machine learning compiler for GPUs, CPUs, and ML accelerators, useful for building AI-powered applications.
ilya-zlobintsev/LACT
A Linux-based GPU configuration and monitoring tool written in Rust for AMD and Nvidia GPUs.
acidanthera/WhateverGreen
A library of various patches necessary for certain ATI/AMD/Intel/Nvidia GPUs on macOS.
NVIDIA/TransformerEngine
A high-performance Transformer library for accelerating AI models on NVIDIA GPUs, including low-precision support.
ARM-software/ComputeLibrary
A computer vision and machine learning library optimized for Arm CPUs and GPUs using SIMD technologies.
pytorch/TensorRT
PyTorch compiler for NVIDIA GPUs using TensorRT, enabling efficient deep learning inference on CUDA hardware.
BBuf/how-to-optim-algorithm-in-cuda
This repository provides guidance on optimizing algorithms for CUDA, a framework for parallel computing on NVIDIA GPUs.
NVIDIA/gpu-operator
NVIDIA GPU Operator manages GPUs in Kubernetes for developers building AI-powered applications.
microsoft/DirectML
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning tasks on a variety of GPUs.
openlit/openlit
An open-source platform for AI engineering with LLM observability, GPU monitoring, and prompt management tools.
NVIDIA/cutile-python
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs in Python.
XiongjieDai/GPU-Benchmarks-on-LLM-Inference
Compares the performance of multiple NVIDIA GPUs and Apple Silicon for running large language model inference.
kevmo314/scuda
SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
AdaptiveCpp/AdaptiveCpp
A community-driven C++ compiler for heterogeneous programming models like SYCL, C++ parallelism, and CUDA/HIP.
nestrilabs/nestri
A cloud-based platform for deploying and streaming games/apps, with support for various gaming technologies.
Xtra-Computing/thundersvm
A fast and scalable SVM library for classification and regression tasks on GPUs and CPUs.
Tencent/tgfx
A high-performance 2D graphics library for modern GPUs, supporting text, image, and vector rendering across platforms.
Zaneham/BarraCUDA
Open-source CUDA compiler that targets AMD GPUs, compiling CUDA code to GFX11/12 machine code.
NVIDIA/nccl-tests
NCCL Tests - a library for efficient multi-GPU collective communication primitives for NVIDIA GPUs
Stay in the loop
Get weekly updates on trending AI coding tools and projects.