Drop `--iree-llvmcpu-enable-microkernels`, replaced by `--iree-llvmcpu-enable-ukernels` (#15646) This old flag (`-microkernels`) was a boolean. The new flag (`-ukernels`) is a string. Porting guide: - If you were passing `--iree-llvmcpu-enable-microkernels` (or equivalently, `...=true`), the equivalent new flag is `--iree-llvmcpu-enable-ukernels=all`. You may however choose to do `--iree-llvmcpu-enable-ukernels=mmt4d` instead if you want to only enable the mmt4d ukernel and not all future ukernels that may be added in the future. - If you were passing `--iree-llvmcpu-enable-microkernels=false`, that was the default behavior anyway so that wasn't having any effect, so you could drop that; however, if you meant to explicitly opt out of ukernels whenever they would become default, the equivalent of that with the new flag is `--iree-llvmcpu-enable-ukernels=none`. All occurences of the old flag in the IREE repo have already been replaced. Please confirm when it's OK to proceed with this, @mariecwhite @pzread @dcaballe @jpienaar @lundong @hcindyl @banach-space .
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.