commit | 554363df23132dbf7f5a7099c10e49bf3f7e86e8 | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Sat Aug 07 19:02:04 2021 -0700 |
committer | GitHub <noreply@github.com> | Sat Aug 07 19:02:04 2021 -0700 |
tree | dbaf6eed53f7c76a3045edb8e9d32b33a64350fc | |
parent | b73178e527ee261c0847c7f9b60881f06e995177 [diff] |
Improving trace yaml ergonomics by matching the command line parsers. (#6689) We now accept the following buffer view forms (mix/match as needed): ```yaml - type: hal.buffer_view shape: 4 element_type: f32 contents: 5 2 3 4 - type: hal.buffer_view shape: - 4 element_type: 50331680 contents: !!binary | AACAQAAAIEEAAJBBAADgQQ== ``` And a special list item that is parsed as a tensor and expands to the same buffer view as above: ```yaml - !hal.buffer_view 4xf32 - !hal.buffer_view 4xf32=2 - !hal.buffer_view 4xf32=2 2 2 2 ```
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.