Repository files navigation

IREE (IntermediateRepresentationExecutionEnvironment,pronounced as "eerie") is anMLIR-based end-to-endcompiler and runtime that lowers Machine Learning (ML) models to a unified IRthat scales up to meet the needs of the datacenter and down to satisfy theconstraints and special considerations of mobile and edge deployments.

Seeour website for project details, userguides, and instructions on building from source.

• 2025-04-02:AMD submitted an IREE-based SDXL implementation to the MLPerf benchmark suite
• 2024-05-23:IREE joins the LF AI & Data Foundation as a sandbox-stage project

Releases notes arepublished on GitHub releases.

Package	Release status
GitHub release (stable)
GitHub release (nightly)
iree-base-compiler
iree-base-runtime

For more details on the release process, seehttps://iree.dev/developers/general/release-management/.

Operating system	Build status
Linux
macOS
macOS

For the full list of workflows seehttps://iree.dev/developers/general/github-actions/.

• GitHub issues: Feature requests,bugs, and other work tracking
• IREE Discord server: Daily developmentdiscussions with the core team and collaborators
• (New)iree-announce email list:Announcements
• (New)iree-technical-discussion email list:General and low-priority discussion
• (Legacy)iree-discuss email list:Announcements, general and low-priority discussion

• MLIR topic within LLVM Discourse:IREE is enabled by and heavily relies onMLIR. IREEsometimes is referred to in certain MLIR discussions. Useful if you are alsointerested in MLIR evolution.

Seeour website for more information.

Community meeting recordings:IREE YouTube channel

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