| commit | c3b3d96ec2d8aef64e678a6f2265ff0b92cf7034 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Tue Feb 20 15:41:16 2024 -0800 |
| committer | GitHub <noreply@github.com> | Tue Feb 20 23:41:16 2024 +0000 |
| tree | 1dd210e7cfc114a3345f3269cf8af2f9078bac7c | |
| parent | dbb43c85e52363c102c9c575fbe33f94e39f8472 [diff] |
Adding hal.device.id queries to HAL devices. (#16495) This allows for the compiler to query whether a particular device ID (`cuda`, `local-task`, etc) matches a pattern string (`local-*`, etc). Today all devices just report on whatever ID they were assigned by their driver but we could support other HAL driver matches in the future (for things like remote devices that may expose multiple subdevices). Note that this is not a vendor identifier (like `NVIDIA GeForce ..`).
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.