commit | 3bdcea8dfbd4b4919665621f13c092ab207a0022 | [log] [tgz] |
---|---|---|
author | Han-Chung Wang <hanchung@google.com> | Wed May 19 08:35:23 2021 +0800 |
committer | GitHub <noreply@github.com> | Wed May 19 08:35:23 2021 +0800 |
tree | acdd935a2cd42b877be95a24f80f668a107f3079 | |
parent | 90368f18f168932c9082b996d9d29e049faaf217 [diff] | |
parent | eac55b6464b328d9264f6bb6a15f5b0fb74a4130 [diff] |
Merge google -> main (#5947) * eac55b646 Merge pull request #5944 from hanhanW:main-to-google * 24b5f7e0e Synchronize submodules with LLVM at llvm/llvm-project@638166458008 * b82ab2a79 Separate CHLO transforms for expanding compositions and lowering broadcasts. * 6d1110647 Integrate LLVM at llvm/llvm-project@638166458008 * 50166531f Integrate LLVM at llvm/llvm-project@560b709abedc * 28f666984 Integrate LLVM at llvm/llvm-project@f8dbd6107417 * 1104d0ba5 Integrate LLVM at llvm/llvm-project@3bc2b97b34ff * 7fc3dda1d Integrate LLVM at llvm/llvm-project@e2e1a78abcef
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler that lowers Machine Learning (ML) models to a unified IR optimized for real-time inference on mobile/edge devices against heterogeneous hardware accelerators. IREE also provides flexible deployment solutions for its compiled ML models.
See our website for project details, user guides, and instructions on building from source.
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!
IREE is licensed under the terms of the Apache license. See LICENSE for more information.