#machine-learning

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow has everything you need to build a computer vision application.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

Scalable machine 🤖 learning for time series forecasting.

A library for training and deploying machine learning models on Amazon SageMaker

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Accessible large language models via k-bit quantization for PyTorch.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

ML.NET is an open source and cross-platform machine learning framework for .NET.

Structured Outputs

Flower: A Friendly Federated AI Framework

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

Optax is a gradient processing and optimization library for JAX.

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Pretrained model hub for Keras 3.

Kubeflow’s superfood for Data Scientists

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

MLRun is an open source MLOps platform for quickly building and managing continuous ML applications across their lifecycle. MLRun integrates into your development and CI/CD environment and automates the delivery of production data, ML pipelines, and online applications.

The Modular Platform (includes MAX & Mojo)

NucliaDB, The AI Search database for RAG

🌊 Online machine learning in Python

Efficient in-memory representation for ONNX, in Python

Python Streaming DataFrames for Kafka

We write your reusable computer vision tools. 💜

sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has you covered.

Synthetic data generation for tabular data