| commit | d284154f65fef2936271dea6d94545c58cc74bca | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Wed Apr 17 14:26:08 2024 -0700 |
| committer | GitHub <noreply@github.com> | Wed Apr 17 21:26:08 2024 +0000 |
| tree | 0ff96117590ebbfb88b3347be48121ab6a832e75 | |
| parent | a8731a37aa94c083f2b8ba9e45dfd18e4ec448fd [diff] |
Making FlattenFullFillToSplat more conservative. (#17079) Full analysis is required to do this in all cases as we need to know that the target storage isn't required to be the same. The pattern now does a local check to see if it can be proven to be producing into a non-tied value it knows the providence of and bails otherwise.
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.