commit | e2e82b30785cbb644f8cb2b9c7efb2b84fe7e4cd | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Sun Jun 27 08:16:44 2021 -0700 |
committer | GitHub <noreply@github.com> | Sun Jun 27 08:16:44 2021 -0700 |
tree | 95f77dd92d04c6793c89f21a0b355dc3098d4a4e | |
parent | 398084f297ce244aef209804a8bf48d542ea6a3c [diff] |
Avoid nesting modules in modules for VM conversion if not needed. (#6320) The implicit outer MLIR module cannot have conversion patterns applied so prior to conversion we create _another_ module and nest it for the module->vm.module conversion to work. If trying to run VM conversion on an already converted module with both the implicit outer module and vm.module nested within this would cause module>module>vm.module to be converted to module>vm.module>vm.module. Fixes #6307.
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.