commit | 3bd115aac2e753a629ebf95ebd54057b8a3a0fe6 | [log] [tgz] |
---|---|---|
author | Scott Todd <scotttodd@google.com> | Fri Jun 09 08:49:23 2023 -0700 |
committer | GitHub <noreply@github.com> | Fri Jun 09 08:49:23 2023 -0700 |
tree | b0ec5148abd69015fb8310ee5ba2bd26226b19b9 | |
parent | c12bf50e92d78d6203fda255f3b47cb0000728b8 [diff] |
Refresh deployment-configuration website pages. (#14013) I started to write a new "compiler tips" page, then I found better places to put those tips within the pages that already exist. While I added the new sections, I proofread the pages and refreshed their structure and style. (I still plan on adding new pages in this "guides" section) | | | |--------|--------| | Current section | https://openxla.github.io/iree/guides/deployment-configurations | | Preview of this PR | https://scotttodd.github.io/iree/guides/deployment-configurations | High level changes: * Add icon prefixes to many sections * Adjust grammar / phrasing * Format tables and code blocks * Remove `--iree-input-type=stablehlo` (auto should work, and TF / StableHLO are not the focus of these pages) * Add sample `iree-run-module --list_drivers` and `iree-compile --iree-hal-list-target-backends` output * Call Metal "experimental" and not "stale" * Add tip for "--iree-llvmcpu-target-cpu-features"
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.