Tensors and Dynamic neural networks in Python with strong GPU acceleration

Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

Efficient in-memory representation for ONNX, in Python

Tutorials for creating and using ONNX models

Open standard for machine learning interoperability

A collection of pre-trained, state-of-the-art models in the ONNX format

Repository for ONNX SIG artifacts

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

Convert scikit-learn models and pipelines to ONNX

ONNXMLTools enables conversion of models to ONNX

Convert TensorFlow models to ONNX

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

A conda-smithy repository for onnx.

Machine Learning Agility (MLAgility) benchmark and benchmarking tools

The fundamental package for scientific computing with Python.

ONNX Runtime: cross-platform, high performance scoring engine for ML models

Pythonic framework for constructing ONNX graphs.

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python. ⚠️ ONNX Script is in very early and active development and is not ready for production.

GitHub App that enforces the Developer Certificate of Origin (DCO) on Pull Requests

Accelerate PyTorch models with ONNX Runtime

Dockerfiles and scripts for ONNX container images

Scoreboard for ONNX Backend Compatibility

Create UIs for prototyping your machine learning model in 3 minutes

The Runner for GitHub Actions 🚀

A conda-smithy repository for onnxruntime.

Seamless operability between C++11 and Python

Tensorflow Backend for ONNX