saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-14 18:12:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/docs/execution-providers/ROCm-ExecutionProvider.md
Faith Xu d4497b9ecd
[Docs] Update EP ordering (#13564) 
### Description
- Update EP ordering and distinguish between MS-maintained and
community-maintained EPs
- Update CUDA version table for v1.13
- Staged preview:
https://faxu.github.io/onnxruntime/docs/execution-providers/
2022-11-07 10:02:01 -08:00

1.5 KiB
Raw Blame History

title description parent nav_order redirect_from
AMD - ROCm Instructions to execute ONNX Runtime with the AMD ROCm execution provider Execution Providers 10 /docs/reference/execution-providers/ROCm-ExecutionProvider

ROCm Execution Provider

{: .no_toc }

The ROCm Execution Provider enables hardware accelerated computation on AMD ROCm-enabled GPUs.

Contents

{: .no_toc }

  • TOC placeholder {:toc}

Install

Pre-built binaries of ONNX Runtime with ROCm EP are published for most language bindings. Please reference Install ORT.

Requirements

ONNX Runtime ROCm
main 5.2.3
1.12 5.2.3
1.12 5.2

Build

For build instructions, please see the BUILD page.

Usage

C/C++

Ort::Env env = Ort::Env{ORT_LOGGING_LEVEL_ERROR, "Default"};
Ort::SessionOptions so;
int device_id = 0;
Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_ROCm(so, device_id));

The C API details are here.

Python

Python APIs details are here.

Performance Tuning

For performance tuning, please see guidance on this page: ONNX Runtime Perf Tuning

Samples

Python

import onnxruntime as ort

model_path = '<path to model>'

providers = [
    'ROCmExecutionProvider',
    'CPUExecutionProvider',
]

session = ort.InferenceSession(model_path, providers=providers)