| commit | dc6f0cd5f4a784531bde3dcac48f2effc28c4224 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Mon Nov 20 21:36:58 2023 -0800 |
| committer | GitHub <noreply@github.com> | Mon Nov 20 21:36:58 2023 -0800 |
| tree | d1a1652f9092b4e93f44f0635904ef2a4fdc6cc1 | |
| parent | 8ff8a848379882ed4a32a46d4192c457c535e46c [diff] |
Adding multiple_modules sample (and fixing bugs). (#15653) This demonstrates multiple VM modules calling each other in both synchronous and asynchronous modes. This is useful for both designing reusable components as well as during testing/development/benchmarking as it shows how easily pipelines can be constructed for running models that may have state or non-trivial call sequences. Users can make as many calls as they want or have their own state or control flow in the pipelines to build arbitrarily complex sequences of work without needing to author python/C/yaml for iree-run-trace.
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.