Mirror of https://github.com/openxla/iree

Clone this repo:
  1. 4a80ee3 [LLVMGPU] Nuke logic that is trying to simplify thread id arithmetic (#16507) by Quinn Dawkins · 8 hours ago main
  2. ede9135 [rocdl] Fix kernel config when there is no valid intrinsic (#16509) by Quinn Dawkins · 9 hours ago latest-snapshot
  3. 4ee81fa [rocdl] Permute to create nested layout matching contraction (#16496) by Lei Zhang · 10 hours ago
  4. 5cdd6ec Limit release index API requests to the first 1000 releases. (#16506) by Scott Todd · 10 hours ago
  5. 884d2dc [HIP] Add device cast to fix build error (#16505) by Nithin Meganathan · 12 hours ago

IREE: Intermediate Representation Execution Environment

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 datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.

See our website for project details, user guides, and instructions on building from source.

CI Status IREE Discord Status

Project Status

IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!

Communication Channels

Related Project Channels

  • MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

Architecture Overview

IREE Architecture IREE Architecture

See our website for more information.

Presentations and Talks

License

IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.