commit | 22f04e91d15a66441813927ef354fd057581185e | [log] [tgz] |
---|---|---|
author | Matthias Springer <me@m-sp.org> | Wed May 31 14:51:21 2023 +0200 |
committer | GitHub <noreply@github.com> | Wed May 31 12:51:21 2023 +0000 |
tree | 760560d29e91567f433472f7414aa6b8426a490e | |
parent | a6aa49b12c4a509b2258f3c814ceb40ee0b06d73 [diff] |
Better TrackingListener error messages (#13756) * Include the transform op and replacement details when the ErrorCheckingTrackingListener failed to find a replacement op. * Simplify ErrorCheckingTrackingListener: store the last error in the listener object and assert that error was reset in the destructor. * To simply the API, check listener failures and other errors separately (do not chain errors).
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!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.