A modern model graph visualizer and debugger

Experimental projects related to TensorRT

MLIR For Beginners tutorial

library to read/write .npy and .npz files in C/C++

Automated releases for torch-mlir

Goal: Enable awesome tooling for Bazel users of the C language family.

Tensor Compute Primitives: Mid-level Intermediate Representation for Machine Learning Programs

An open-source ML pipeline development platform

Run compilers interactively from your web browser and interact with the assembly

Examples for Bazel

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

Copybara: A tool for transforming and moving code between repositories.

PyTorch tutorials.

C++ extensions in PyTorch

Gin provides a lightweight configuration framework for Python

Inference of quantization aware trained networks using TensorRT

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

Open Source Compiler Framework using ONNX as Frontend and IR

a GitHub action to run `pre-commit`

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

The Sphinx documentation generator

GitHub Actions for GitHub Pages 🚀 Deploy static files and publish your site easily. Static-Site-Generators-friendly.

Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Intel® Data Center GPUs

Dataflow compiler for QNN inference on FPGAs

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Examples for using ONNX Runtime for model training.