Fixing issues found when enabling indirect command buffers. (#18382) This is in preparation for making `--iree-hal-indirect-command-buffers=true` the default as part of #17875. Most of the fixes required were related to analysis failures that required stricter handling of duplicate call graph traversal and care around when initializers are combined (which still needs improvement but at a general level not related to this work). A TODO was fixed for supporting `stream.cmd.call` in reusable command buffers by passing binding table ordinals along with buffers to the `stream.cmd.func` ops once lowered into the HAL dialect - there are no users of this functionality today but now it won't be a special case.
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.