| commit | e77c78e7ac1c3c24870a54ea2529b742707713e3 | [log] [tgz] |
|---|---|---|
| author | Stella Laurenzo <stellaraccident@gmail.com> | Mon Sep 25 16:41:59 2023 -0700 |
| committer | GitHub <noreply@github.com> | Mon Sep 25 23:41:59 2023 +0000 |
| tree | 1ccebbbd5d992e255f1632ce0656f36f6c4f1138 | |
| parent | 3725acd3d64d0a9014718d44f0b795b883b64374 [diff] |
Add a dedicated 'torch' input pipeline. (#15037) This has been in use downstream via the `torch-to-iree` pass and is now ready to be exposed as a real input type. As of https://github.com/nod-ai/SHARK-Turbine/pull/72, Turbine can now generate pure 'torch' level programs that can be fed to IREE directly with this input pipeline. We expect that this will be more stable and supportable vs half-lowering to IREE internal dialects in the frontend.
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.