commit | 27e7a9058eded6a20dc098368352329263f77a23 | [log] [tgz] |
---|---|---|
author | Han-Chung Wang <hanhan0912@gmail.com> | Tue Jan 14 20:50:54 2025 -0800 |
committer | GitHub <noreply@github.com> | Tue Jan 14 20:50:54 2025 -0800 |
tree | 83739f287ee95a29693ff8146482a4dcf0ae6b99 | |
parent | a953763e6a128ab9413a8bc93df9aa2c8f99ec9e [diff] |
[DT][Encoding] Use layouts to calculate storage size when it is present. (#19686) The revision implements the `calculateStorageSizeInBytes` method for backend attributes, so the EncodingAttr can query the storage size from each layout when layouts are set. It enables the storage size request propagation from devices to hosts through interfaces. The tests are adapted from existing tests with resolved layouts. Additionally, it adds a new test that has two different layouts. It computes both of them and select the maximum size. The revision also implements the output streaming and log the final tile size decision in CPUEncodingExternalModels, which helps debug easier. --------- Signed-off-by: hanhanW <hanhan0912@gmail.com>
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.
Releases notes are published on GitHub releases.
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-base-compiler | |
Python iree-base-runtime |
Operating system | Build status |
---|---|
Linux | |
macOS | |
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
Date | Title | Recording | Slides |
---|---|---|---|
2021-06-09 | IREE Runtime Design Tech Talk | recording | slides |
2020-08-20 | IREE CodeGen (MLIR Open Design Meeting) | recording | slides |
2020-03-18 | Interactive HAL IR Walkthrough | recording | |
2020-01-31 | End-to-end MLIR Workflow in IREE (MLIR Open Design Meeting) | recording | slides |
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.