| commit | 3bf20db08afb799c06f87efdc9ef0281d7a973c6 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Fri Sep 22 16:51:12 2023 -0700 |
| committer | GitHub <noreply@github.com> | Fri Sep 22 16:51:12 2023 -0700 |
| tree | 5f6bda86905393d776d4622e26d61b76c8c15b34 | |
| parent | 875fde352123cd69d4eae2dba609a377de03d3c7 [diff] |
Fixing hal_inline file IO for variable initialization. (#15022) This corrects the assumption in #14880 that all I/O would be loading into constants. Now we support the file I/O from constant buffers only by making copies. If we support file I/O on program ABI boundaries in the future (passing in a `!hal.file` as an argument/etc) we may need to change things but the hal_inline target isn't really intended for general programs doing arbitrary I/O.
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.