| commit | 9234f428b05141f6a7ec61ad3ebc2a777edb4705 | [log] [tgz] |
|---|---|---|
| author | Stella Laurenzo <stellaraccident@gmail.com> | Mon Feb 12 09:17:28 2024 -0800 |
| committer | GitHub <noreply@github.com> | Mon Feb 12 09:17:28 2024 -0800 |
| tree | 47e76b24cdda49dc72824095113477861dd3869a | |
| parent | d19a9d10a19a0dc1042a781e5bba7b23dcefd088 [diff] |
Add a number of runtime python bindings and refine the HalFence.wait() behavior. (#16371) * Adds static methods to `HalElementType`: `is_byte_aligned`, `dense_byte_count` * Binds the ref protocol for `HalBuffer` so it can be be put in lists. * Adds `HalBufferView.byte_length` * Adds `HalFence.signal` and `HalFence.fail` * Changes behavior of `HalFence.wait` to return False if not satisfied due to timeout and True if satisfied. Raises a Python exception on either synchronous or asynchronous failure. The prior behavior raised exceptions for timeout and reported success on asynchronous failure. The latter is a bug, and the former is just a bad practice (i.e. don't raise exceptions for normal behavior).
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.