| commit | 618c83502b08de6fb080d4037e7fd3af50eaabb4 | [log] [tgz] |
|---|---|---|
| author | Lei Zhang <antiagainst@gmail.com> | Thu Nov 02 22:28:51 2023 -0700 |
| committer | Lei Zhang <antiagainst@gmail.com> | Mon Nov 06 08:16:22 2023 -0800 |
| tree | d1ddfcbd6b247a6f8a1b2dc7ade576ceb5b6a73f | |
| parent | e3671a59e1b1e80e04c6dee2e4c99b4ed9dfcfd6 [diff] |
[cuda] Port over CUDA stream-based command buffer impl This commit uses existing CUDA HAL driver's stream command buffer implementation. Improvements include removing context wrapper and adding various Tracy tracking markers. Various places are cleaned up, e.g., barrier/event impl. Inline execution support is dropped due to its incompatibility with semaphores and recorded command buffers. With it now we can enable CUDA stream-based tests.
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.