commit | a69694fb0a896e714f104ebd82924c9126445b0f | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Fri Nov 19 11:58:38 2021 -0800 |
committer | GitHub <noreply@github.com> | Fri Nov 19 11:58:38 2021 -0800 |
tree | fe77a88572d80b7525df5082f5aa2f14500c3df4 | |
parent | c3505092c2ec709c86e9cfe73fc68b06d730c70e [diff] |
Add TFLite benchmarks for formerly TF models (#7645) These benchmarks align very well with the existing TF source benchmarks but don't involve going through our less-well-supported TF source integration or storing unstable MLIR artifacts. I did a comparison of benchmarks before and after on my Pixel 4 dev phone, manually rewriting the model source in the former so that a direct comparison was possible with existing tooling. No benchmarks have significant changes: https://gist.github.com/GMNGeoffrey/bce029bf4697f9b3deda3bb217b0c6b3
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.