commit | faa0f69baba6f03ae3bcd8b6a261d60ca8d11114 | [log] [tgz] |
---|---|---|
author | Stella Laurenzo <stellaraccident@gmail.com> | Mon Jul 10 15:41:33 2023 -0700 |
committer | GitHub <noreply@github.com> | Mon Jul 10 15:41:33 2023 -0700 |
tree | 87491cbd64a6b109e7a8104b17b7e828febfb911 | |
parent | 36a8d572d1ba37f71f54c947ccd56dccf1c88151 [diff] |
Make the MLIRInterop.h APIs more ergonomic. (#14359) The previous APIs didn't really have a way to manage context or module lifetimes that may conflict with what the caller needs. Now we have these APIs: * ireeCompilerSessionBorrowContext * ireeCompilerSessionStealContext * ireeCompilerInvocationImportBorrowModule * ireeCompilerInvocationImportStealModule Among other things, this allows us to transfer ownership of context/modules in a way that is compatible with the MLIR Python API (which generally must own everything it sees).
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.