| commit | 583cd6fe93510e8c2d373e3909d362a2cd26e99f | [log] [tgz] |
|---|---|---|
| author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Mon Feb 12 21:45:59 2024 -0800 |
| committer | GitHub <noreply@github.com> | Tue Feb 13 05:45:59 2024 +0000 |
| tree | 12b7f511a82383ac3d5ed8506f15b36aa1b8cb8c | |
| parent | 7fdb581136358c0474bc597aa0eb5ea734b6a38f [diff] |
Add sample to match subgraph and call implementation in system plugin. (#16356) This adds a sample that uses a transform dialect script to match an MLP DAG and replaces with a dispatch that uses an external function for the actual implementation. The implementation is provided using as system plugin. This also refactors the matcher to allow for matching implicit capture within region of ops, as long as the captured value is part of input or the matched ops. Follow up to this will be to add some transform dialect ops that handle some of the boiler plate.
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.