commit | b17a65e5b64392e5744984a8ae147caed894186f | [log] [tgz] |
---|---|---|
author | Stella Laurenzo <stellaraccident@gmail.com> | Mon May 09 21:15:19 2022 -0700 |
committer | GitHub <noreply@github.com> | Mon May 09 21:15:19 2022 -0700 |
tree | 5529d6b9d72f4f6c801a9aa698525964ea57b514 | |
parent | ec0dfa46f0e2aa99b0a83cb0e0eca38907d6a25d [diff] |
Re-organize the runtime python directory to be more extensible. (#9071) * Native library goes from iree/runtime/_binding.so -> iree/_runtime.so * Make iree/runtime/_binding.py a trampoline to the correct runtime module. In the future, this will allow us to use a different native implementation based on environment and other packages installed (i.e. would allow an iree-runtime-instrumented and iree-runtime-debug to co-exist and be selected at runtime). * Move tests to a top-level tests directory (common convention). * Move native code to the top-level. * Adds a package_test which builds/installs the package to a venv and does some sanity checking of the modules and scripts (takes about ~12s to run on my machine, so should be hidden in the noise of bigger tests). See #9080 for updating docker images and actually enabling package_test.
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.