> ML_LIBRARIES_CATALOG_v1.0
Qualified ML Libraries
Every library is independently qualified with primary citations, supported version ranges, hardware accelerator separation, and real-world failure patterns.
ONNX Runtime
Microsoft / Linux Foundation AI & Data
Cross-platform, high-performance ML inferencing and training accelerator.
Triton Inference Server
NVIDIA
Enterprise inference serving software for high-throughput, multi-framework model deployment.
OpenVINO
Intel
Open-source toolkit for optimizing and deploying AI inference on Intel hardware.
TensorRT
NVIDIA
High-performance deep learning inference optimizer and runtime by NVIDIA.
Apache TVM
Apache Software Foundation
An end-to-end deep learning compiler for CPUs, GPUs and specialized accelerators.
ExecuTorch
Meta / PyTorch Foundation
End-to-end solution for enabling on-device AI across mobile and edge devices for PyTorch.
TensorFlow Lite
Deploy machine learning models on mobile and edge devices.
Core ML
Apple
Integrate machine learning models into your Apple app with hardware acceleration.
WebLLM
MLC AI
High-performance in-browser LLM inference engine powered by WebGPU.
scikit-image
scikit-image Development Team / NumFOCUS
Peer-reviewed scientific image processing algorithms built natively on NumPy.
OpenCV
OpenCV Foundation / Open Source Vision Foundation
The foundational open-source computer vision and video processing library.
torchvision
PyTorch Foundation / Meta
Official PyTorch library for computer vision datasets, architectures, and transforms.
timm (PyTorch Image Models)
Ross Wightman / Hugging Face
The definitive collection of PyTorch vision architectures, pretrained weights, and training recipes.
Ultralytics (YOLO)
Ultralytics Inc.
The industry-standard framework for real-time object detection, segmentation, and pose tracking.
Detectron2
Meta FAIR (Fundamental AI Research)
Meta FAIR's modular deep learning platform for object detection and instance segmentation.
MMDetection
OpenMMLab
OpenMMLab's comprehensive toolbox implementing over 70 object detection and segmentation architectures.
Albumentations
Albumentations Team
High-performance image augmentation library for deep learning computer vision.