| commit | 0066c7a5f033d29be645845a7b58e95631bbf41e | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Mon Nov 21 16:19:42 2022 -0800 |
| committer | Ben Vanik <ben.vanik@gmail.com> | Mon Dec 05 17:53:23 2022 -0800 |
| tree | 09cd1e1445903313a2d670f484d9615df55f9b07 | |
| parent | a0ab5e5ea1fae1f5f910683c5277c0f805b367b5 [diff] |
Adding initial stream.async.collective op. It's modeled like stream.async.copy (for better or worse at least consistent) but will likely change as part of #11249 for supporting in-place collectives (or, stream.async.copy will be updated for memmove-like behavior). Locations in the code that need updating have been marked with a TODO. The send/recv ops are not yet modeled and will likely be done as dedicated ops due to their unary operand/result nature.
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.