编译器与运行时是两个独立 PyPI 包,需分别安装;README 未给出具体编译命令,需查阅官网文档;从源码构建的说明不在 README 内,需访问 iree.dev。
iree
iree-orgApache-2.0活跃维护基于 MLIR 的可重定向机器学习编译器与运行时工具包,把 PyTorch、TensorFlow、JAX、ONNX 等模型编译到 CPU、CUDA、ROCm、Vulkan 等多种硬件上运行。
A retargetable MLIR-based machine learning compiler and runtime toolkit.
pip install iree-base-compiler
pip install iree-base-runtimeREADME 未说明具体显存、CPU 或 GPU 型号要求,仅提及目标覆盖数据中心、移动与边缘部署。
基于 MLIR 的端到端 ML 编译器与运行时,把模型编译成统一 IR,覆盖数据中心到移动边缘
基于 MLIR 的可重定向机器学习编译器与运行时工具包,把 PyTorch、TensorFlow、JAX、ONNX 等模型编译到 CPU、CUDA、ROCm、Vulkan 等多种硬件上运行。
核心能力
- 用 MLIR 将 ML 模型降为统一 IR
- 同一套编译产物从数据中心扩展到移动边缘
- 提供编译器与运行时两部分工具链
- 发布 PyPI 包 iree-base-compiler 与 iree-base-runtime
- 支持 GPU CodeGen 与 SPIR-V 后端
容易踩的坑
- iree-3.14.0rc20261108iree candidate iree-3.14.0rc20261108pre-release最新正式版2026-11-08 · 2026-11-08 10:00 UTC
Automatic candidate release of iree.
- iree-3.14.0rc20261107iree candidate iree-3.14.0rc20261107pre-release2026-11-07 · 2026-11-07 09:14 UTC
查看更新说明
Automatic candidate release of iree.
- iree-3.14.0rc20261106iree candidate iree-3.14.0rc20261106pre-release2026-11-06 · 2026-11-06 11:05 UTC
查看更新说明
Automatic candidate release of iree.
- iree-3.13.1Release v3.13.1pre-release2026-11-06 · 2026-11-06 04:50 UTC
查看更新说明
Highlights in IREE v3.13.1 Patch Release
Runtime
- Restores VM bytecode verifier validation of register ordinals and tightens related register and type checks. Users of
iree-base-runtime3.10.0 through 3.13.0 should upgrade to 3.13.1. https://github.com/iree-org/iree/pull/25088
Build infrastructure
- Uses the official ROCm distribution for AMD device bitcode after the legacy artifact was retired. https://github.com/iree-org/iree/pull/25133
Full Changelog: https://github.com/iree-org/iree/compare/v3.13.0...iree-3.13.1
- Restores VM bytecode verifier validation of register ordinals and tightens related register and type checks. Users of
- iree-3.14.0rc20261104iree candidate iree-3.14.0rc20261104pre-release2026-11-04 · 2026-11-04 11:04 UTC
查看更新说明
Automatic candidate release of iree.
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
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.
Project news
- 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
Project status
Release status
Releases notes are published 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, see https://iree.dev/developers/general/release-management/.
Build status
Nightly build status
| Operating system | Build status |
|---|---|
| Linux | |
| macOS |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
Communication channels
- GitHub issues: Feature requests, bugs, and other work tracking
- IREE Discord server: Daily development discussions 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
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
See our website for more information.
Presentations and talks
Community meeting recordings: IREE YouTube channel
| Date | Title | Recording | Slides |
|---|---|---|---|
| 2025-06-10 | Data-Tiling in IREE: Achieving High Performance Through Compiler Design (AsiaLLVM) | recording | slides |
| 2025-05-17 | Introduction to GPU architecture and IREE's GPU CodeGen Pipeline | recording | slides |
| 2025-02-12 | The Long Tail of AI: SPIR-V in IREE and MLIR (Vulkanised) | recording | slides |
| 2024-10-01 | Unveiling the Inner Workings of IREE: An MLIR-Based Compiler for Diverse Hardware | recording | |
| 2021-06-09 | IREE Runtime Design Tech Talk | recording | slides |
| 2020-08-20 | IREE CodeGen (MLIR Open Design Meeting) | recording | slides |
| 2020-03-18 | Interactive HAL IR Walkthrough | recording | |
| 2020-01-31 | End-to-end MLIR Workflow in IREE (MLIR Open Design Meeting) | recording | slides |
License
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.
