commit | 890bdc968dfde9fd2feaee7d7046168f857cffd3 | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Tue Jul 30 12:55:58 2024 -0700 |
committer | GitHub <noreply@github.com> | Tue Jul 30 19:55:58 2024 +0000 |
tree | 7e2db405c83ac6b9ca59783cdd09c9c915da669f | |
parent | cb5f32dbbb47d5dc222e723b4f12d7a292a6378e [diff] |
Removing extraneous iree/hal/drivers/utils. (#18050) We want to keep the total number of targets reasonable and having a new target for a single helper is not worth the cost. We also already have a utils directory meant for HAL implementations to use and it should have been in there. Since this method is simple it's been added to the core HAL header (usually not preferred, but in the case of semaphore_list its a basic utility and not a vtabled type that will have different behavior between implementations).
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.