commit | 48fb79ca9b246306098d2726c30dc853c808d9aa | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Tue Jan 04 10:15:08 2022 -0800 |
committer | GitHub <noreply@github.com> | Tue Jan 04 10:15:08 2022 -0800 |
tree | 4d207db063aee6cbbc5118624724adb561d00c48 | |
parent | 1b0fc02c5ff535e829626a270940e29ee91d4664 [diff] | |
parent | 323b9c3a9f588450e1d12a52a6cb321cda4d4f8d [diff] |
Merge pull request #7990 from google/benvanik-trim This routes notifications to both system and user modules in the VM on suspend/resume and low memory warnings. System modules can implement a notify method for internal handling and here the HAL is extended to trim its pools. The compiler will be able to add a `__notify` export to generated modules that handles end-user resources (computed state from initializers, compiler-owned pools, etc) and we could extend this all the way up to the frontend as a discardable attribute.
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.