| commit | 60ac3330b8ea9bcd6af4c7db20d2aa31a523491a | [log] [tgz] |
|---|---|---|
| author | Stella Laurenzo <stellaraccident@gmail.com> | Tue Feb 13 18:55:12 2024 -0800 |
| committer | GitHub <noreply@github.com> | Tue Feb 13 18:55:12 2024 -0800 |
| tree | 11517bdd114b2b60fd0fd0eb1b9baf89db690b26 | |
| parent | c8b6dc1539e2b1918b37fa30b072081784b72f67 [diff] |
[python] Add a HalDeviceLoop class for routing runtime events to futures. (#16385) This is the most basic level of interop possible with the asyncio system in Python. As noted offline when we were looking at this, the test case chosen seems to be exposing a synchronization bug in local-task, causing a wait to not return even though there are signaled handles. This does not (can not) occur in local-sync, and appears to not be an issue in vulkan. As such, landing with local-sync so that we can iterate further.
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.