| commit | 69eb9ca3587500fd727dcff97b25e6793d1323eb | [log] [tgz] |
|---|---|---|
| author | bjacob <benoitjacob@google.com> | Mon Jul 10 11:04:53 2023 -0400 |
| committer | GitHub <noreply@github.com> | Mon Jul 10 11:04:53 2023 -0400 |
| tree | 3630590a9bb9b8d4e969aed35a648cfd9f4496dc | |
| parent | ac34d7b7261173cc583c1874dc129242dfd3deec [diff] |
Remove the ukernels standalone plugin (#14339) This was done as a stepping stone towards ukernels-as-bitcode. Now that we have that, we don't need the stepping stone anymore. Like the bitcode build, this involved custom invocations of custom Clang to produce a multi-arch library; this is expensive to maintain as it's a whole separate build of all ukernel code to all target architectures. The system-plugin remains as it's much simpler (it simply links the native-build of ukernels as a regular library) and it's much more likely to still be used by some classes of users going forward (people going to places where only a system-provided toolchain can go, and not caring for the multi-arch aspect).
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.