commit | 2c638f31a413a9d36a2b97a61fa0c179b8a62542 | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Tue Jul 30 10:36:40 2024 -0700 |
committer | GitHub <noreply@github.com> | Tue Jul 30 17:36:40 2024 +0000 |
tree | 9907c538da72c5c9c033c27afff8392fc6dbb275 | |
parent | 742fd24b9338c42961c8b9de4b3ca08b885dd3d8 [diff] |
Adding `once` attribute to `stream.cmd.execute`. (#18043) For now we set this flag only if the op is used in the entry block of an initializer. A must-be-executed analysis (and others) could be run to set it instead for cases where we call functions from initializers but we don't tend to do that today. Progress on #17875.
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.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.