commit | 348dd47f74816fdeac1a061f1bac1f05c598929a | [log] [tgz] |
---|---|---|
author | Ben Vanik <ben.vanik@gmail.com> | Thu Oct 31 11:41:45 2024 -0700 |
committer | GitHub <noreply@github.com> | Thu Oct 31 11:41:45 2024 -0700 |
tree | a7d302b3f379826d73fb0d2dac2d493752d551e3 | |
parent | df2b8a4b6e7b1b24cc48ad80c42d55da5379273e [diff] |
Adding a HAL module debug sink interface. (#18966) HAL module creators can now pass in a debug sink that injects callbacks that can be made by the HAL module on request from programs or by the HAL module itself. Today it just has a buffer view trace callback but in the future we could use this to report profiling information or asynchronous errors. A default `iree_hal_module_debug_sink_stdio(file)` is provided that preserves the current behavior of writing trace buffers to stderr (when HAL string utils are enabled). `iree_hal_module_debug_sink_null()` can be used to ensure no string handling code is compiled in if a caller doesn't want it. Callers can also implement whatever behavior they want.
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
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-compiler | |
Python iree-runtime |
Host platform | Build status |
---|---|
Linux | |
macOS | |
Windows |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
See our website for more information.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.