Infrastructure / Compilers & Model Optimization

IREE

IREE is an MLIR-based compiler and runtime that lowers machine learning models to a unified intermediate representation, targeting datacenter hardware at one end and mobile and edge constraints at the other. Input comes from PyTorch, JAX, TensorFlow and ONNX; output targets include CPU, CUDA, ROCm, Vulkan and SPIR-V. The project is hosted by the LF AI & Data Foundation.

Verified 2026-08-18 via the GitHub API and the LICENSE body.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public
core-gated: ungated

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

https://github.com/iree-org/iree/blob/main/LICENSE recorded 2026-08-18
LICENSE file is the verbatim Apache-2.0 text
https://api.github.com/repos/iree-org/iree recorded 2026-08-18
Repo metadata - license spdx_id Apache-2.0, private false, archived false, default branch main - for iree-org/iree.
https://github.com/iree-org/iree/blob/main/README.md recorded 2026-08-18
README describes an MLIR-based end-to-end compiler and runtime that lowers ML models to a unified IR scaling from datacenter hardware down to mobile and edge constraints, with an LF AI & Data project note, with no paid tier, enterprise edition or license-key-gated build beside it.

Adoption

2 high confidence

2.0

76,001 PyPI downloads of `iree-base-compiler` in the trailing 30 days, which lands in the 10K-100K band of the software usage scale, level 2.

https://pypistats.org/api/packages/iree-base-compiler/recent recorded 2026-08-18
last_month downloads = 76,001 for iree-base-compiler

Capability

5 medium confidence

5.0

Banded on the category feature matrix as retargetable end-to-end compiler. Placed level with the apache-tvm anchor, on a matrix that bands on how much of the model-to-hardware transformation pipeline a product performs, over how many inputs and targets.

https://github.com/iree-org/iree/blob/main/README.md recorded 2026-08-18
README still documents an MLIR-based end-to-end compiler and runtime that lowers ML models to a unified IR scaling from datacenter hardware down to mobile and edge constraints, with an LF AI & Data project note.

Verified 2026-08-18