IREE (Intermediate Representation Execution Environment, pronounced as "eerie") is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the data center and down to satisfy the constraints and special considerations of mobile and edge deployments.

Features

  • IREE supports importing from a variety of ML frameworks
  • Documentation available
  • Runs on Windows, Linux, and Mac
  • Ahead-of-time compilation
  • Support for advanced model features
  • Low overhead, pipelined execution
  • Designed for CPUs, GPUs, and other accelerators

Project Samples

Project Activity

See All Activity >

Categories

Machine Learning

License

Apache License V2.0

Follow IREE

IREE Web Site

You Might Also Like
SKUDONET Open Source Load Balancer Icon
SKUDONET Open Source Load Balancer

Take advantage of Open Source Load Balancer to elevate your business security and IT infrastructure with a custom ADC Solution.

SKUDONET ADC, operates at the application layer, efficiently distributing network load and application load across multiple servers. This not only enhances the performance of your application but also ensures that your web servers can handle more traffic seamlessly.
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of IREE!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

C++

Related Categories

C++ Machine Learning Software

Registered

2024-08-08