commit | 2f14059389c9b81ea05e301481cd70f8daec9874 | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Mon Jun 28 12:15:10 2021 -0700 |
committer | GitHub <noreply@github.com> | Mon Jun 28 12:15:10 2021 -0700 |
tree | 3ca3f697ce008411db28ef659aa5b2c430cef55f | |
parent | 98a6ea79b70e70d7022fbcda9464fd3ad8c99bff [diff] |
Remove dependency on llvm-bazel (#6298) Instead we use the Bazel build files now upstream in the LLVM repository. There is a risk here because we can't go back and fix these build files and continue to point at the same commit, so if the LLVM integration into google3 uses a commit with broken build files, we won't be able to update for a bit. I think the real solution to that may be to create our own fork of LLVM where we can happily cherry-pick.
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.
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 2.0 License with LLVM Exceptions. See LICENSE for more information.