commit | a650ab221d382340a83c720fa02dd7836472b87a | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Thu Jun 16 18:03:06 2022 -0700 |
committer | Ben Vanik <ben.vanik@gmail.com> | Mon Jun 27 08:19:41 2022 -0700 |
tree | 7089ff940f2250693b947793b40edcc8c1ef0418 | |
parent | ae579be22cdc52b7a1412383b6a955c77c047c23 [diff] |
Exposing the iree_vm_*_invoke low-level API and rebasing iree_vm_invoke. This new low-level API allows for user scheduling of invocations with (relatively) low overhead (no allocations, non-blocking, etc). iree_vm_invoke has been reworked to use this API and future changes will add more user-friendly higher-level APIs by using iree_loop_t. Some integrations may prefer to use this API even for synchronous-like invocations in order to deal with enforced scheduling (like main thread wasm, which cannot block).
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.