| commit | d318c5476056df3bb981bb4c23559c6dc27e06f1 | [log] [tgz] |
|---|---|---|
| author | Stella Laurenzo <laurenzo@google.com> | Thu Apr 27 17:08:22 2023 -0700 |
| committer | GitHub <noreply@github.com> | Fri Apr 28 00:08:22 2023 +0000 |
| tree | ff4ca6d9eb09145fb27c89c37fdf0cfedaaf4e6c | |
| parent | c7925912b2f76b34335ab3d6949cd87a0c4f6071 [diff] |
Rework iree-run-mlir to operate against the IREE compiler C API. (#12715) This removes some unused functionality while sprinkling in the seeds of something better. Future changes can go deeper on inferring compiler configuration from available devices and such (will need some reworking of run_module.c - I erred on the side of simplicity/reuse today). This isn't meant to be an example of the best way to build an online compiler but instead serve as an in-tree test of something that approximates one.
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.