| commit | 29b8197cfb05c261d28802940b7756f5449b80df | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Fri Oct 13 11:49:34 2023 -0700 |
| committer | GitHub <noreply@github.com> | Fri Oct 13 18:49:34 2023 +0000 |
| tree | c69251ac54768e89520f006a7cca6263527bb963 | |
| parent | 2a42fd30a8df1368d4ad44509c87629ac56bb915 [diff] |
Splitting dispatch annotation from outlining. (#15177) It was always a hack to have the annotations happen during outlining and it's since grown unweildy. Separating also has the benefit of allowing executables that come in from frontends (not outlined/formed by us) being able to be named based on their contents. Note that executable names now don't change which is intentional: executables are not intended to contain a single dispatch and on CPU there's no difference as it already links multiple dispatches into the same executables. CUDA/SPIR-V/etc all need to link dispatches together and maybe this will encourage that ;)
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.