commit | f19eba3beba1e164bea53823533302a0c6e77efc | [log] [tgz] |
---|---|---|
author | Mehdi Amini <aminim@google.com> | Wed Jul 28 21:27:23 2021 -0700 |
committer | Copybara-Service <iree-copybara-bot@google.com> | Wed Jul 28 21:28:19 2021 -0700 |
tree | 4cdceb0f8808c8f9922a996e54e4a97bffc01a8b | |
parent | 6458aa6b8d3bf852945e8d1825a5619deaabdd81 [diff] |
Add `tf_type` dialect to hold the types used in the TensorFlow ecosystem This allows to use the TensorFlow types without depending on the entire tensorflow dialect. This new dialect does not intend to contain operations at the moment. Most of the code is purely moved/split from tensorflow/compiler/mlir/tensorflow/ir/... to tensorflow/core/ir/types/... without any change. The only expected visible change for clients is a C++ namespace change for these types, as well as an MLIR change. Most tests can be mass-updated with: s/!tf\./!tf_type/g s/#tf\./#tf_type/g PiperOrigin-RevId: 387504438
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.