⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm…
☆2,595Apr 27, 2026Updated 6 months ago
Alternatives and similar repositories for DirectML
Users that are interested in DirectML are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fork of TensorFlow accelerated by DirectML☆476Sep 25, 2024Updated 2 years ago
- Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.☆2,404Updated this week
- Samples and Tools for Windows ML.☆1,125Aug 7, 2025Updated last year
- DirectML PluggableDevice plugin for TensorFlow 2☆196Feb 27, 2025Updated last year
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆22,187Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AMD ROCm™ Software - GitHub Home☆6,814Oct 14, 2026Updated 2 weeks ago
- This repo hosts the source for the DirectX Shader Compiler which is based on LLVM/Clang.☆3,682Updated this week
- A Python package for extending the official PyTorch that can easily obtain performance on Intel platform☆2,011Mar 30, 2026Updated 7 months ago
- CUDA on non-NVIDIA GPUs☆15,148Updated this week
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆2,579Aug 15, 2026Updated 2 months ago
- The DirectX Tool Kit (aka DirectXTK12) is a collection of helper classes for writing DirectX 12 code in C++☆1,765Oct 20, 2026Updated last week
- OpenVINO™ is an open source toolkit for optimizing and deploying AI inference☆11,085Updated this week
- Open standard for machine learning interoperability☆21,626Updated this week
- This repo contains the DirectX Graphics samples that demonstrate how to build graphics intensive applications on Windows.☆6,856Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Generative AI with ONNX Runtime☆1,147Updated this week
- Development repository for the Triton language and compiler☆20,481Updated this week
- Stable Diffusion web UI☆2,404Mar 5, 2026Updated 7 months ago
- Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs…☆4,082Updated this week
- HIP: C++ Heterogeneous-Compute Interface for Portability☆4,421Updated this week
- Tensor library for machine learning☆15,554Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆43,269Updated this week
- Engineering specs for DirectX features.☆855Updated this week
- A collection of pre-trained, state-of-the-art models in the ONNX format☆9,843Oct 3, 2026Updated 3 weeks ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- DirectXMath is an all inline SIMD C++ linear algebra library for use in games and graphics apps☆1,816Oct 21, 2026Updated last week
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆36,521Updated this week
- ☆87Sep 21, 2023Updated 3 years ago
- LLM inference in C/C++☆132,630Updated this week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆13,422Oct 9, 2026Updated 3 weeks ago
- Visualizer for neural network, deep learning and machine learning models☆33,625Updated this week
- PlaidML is a framework for making deep learning work everywhere.☆4,567Jul 23, 2023Updated 3 years ago
- Official DirectX headers available under an open source license☆747Updated this week
- ONNXMLTools enables conversion of models to ONNX☆1,174Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆24,007Updated this week
- Open Machine Learning Compiler Framework☆13,879Updated this week
- C++ Library Manager for Windows, Linux, and MacOS☆27,553Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,729Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,731Oct 7, 2026Updated 3 weeks ago
- Little console app to run an ONNX model through ONNX Runtime via the DirectML execution provider.☆26Mar 18, 2025Updated last year
- Easy to integrate memory allocation library for Direct3D 12☆1,046Updated this week