Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update ROCM ORT doc #1564

Merged
merged 5 commits into from
Dec 5, 2023
Merged

Update ROCM ORT doc #1564

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7bc3ded
updated doc
mht-sharma Dec 5, 2023
fdeb0f0
update doc
mht-sharma Dec 5, 2023
5265b11
fix format
mht-sharma Dec 5, 2023
1fb1dea
fix doc
mht-sharma Dec 5, 2023
aab64d4
Update docs/source/onnxruntime/usage_guides/amdgpu.mdx
fxmarty Dec 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 19 additions & 10 deletions docs/source/onnxruntime/usage_guides/amdgpu.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,22 +9,31 @@ This guide will show you how to run inference on the `ROCMExecutionProvider` exe
## Installation
The following setup installs the ONNX Runtime support with ROCM Execution Provider with ROCm 5.7.

#### 1. ROCm Installation
#### 1 ROCm Installation

To install ROCM 5.7, please follow the [ROCm installation guide](https://rocm.docs.amd.com/en/latest/deploy/linux/index.html).
Refer to the [ROCm installation guide](https://rocm.docs.amd.com/en/latest/deploy/linux/index.html) to install ROCm 5.7.

#### 2. PyTorch Installation with ROCm Support
#### 2 Installing `onnxruntime-rocm`

Please use the provided [Dockerfile](https://github.com/huggingface/optimum-amd/blob/main/docker/onnx-runtime-amd-gpu/Dockerfile) example or do a local installation from source since pip wheels are currently unavailable.

**Docker Installation:**

```bash
docker build -f Dockerfile -t ort/rocm .
```

**Local Installation Steps:**

##### 2.1 PyTorch with ROCm Support
Optimum ONNX Runtime integration relies on some functionalities of Transformers that require PyTorch. For now, we recommend to use Pytorch compiled against RoCm 5.7, that can be installed following [PyTorch installation guide](https://pytorch.org/get-started/locally/):

```bash
pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm5.7
# Use 'rocm/pytorch:latest' as the preferred base image when using Docker for PyTorch installation.
```

<Tip>
For docker installation, the following base image is recommended: `rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1`
</Tip>

### 3. ONNX Runtime installation with ROCm Execution Provider
### 2.2 ONNX Runtime with ROCm Execution Provider

```bash
# pre-requisites
Expand All @@ -34,8 +43,8 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# Install ONNXRuntime from source
git clone --recursive https://github.com/ROCmSoftwarePlatform/onnxruntime.git
git checkout rocm5.7_internal_testing_eigen-3.4.zip_hash
cd onnxruntime
git checkout rocm5.7_internal_testing_eigen-3.4.zip_hash

./build.sh --config Release --build_wheel --update --build --parallel --cmake_extra_defines ONNXRUNTIME_VERSION=$(cat ./VERSION_NUMBER) --use_rocm --rocm_home=/opt/rocm
pip install build/Linux/Release/dist/*
Expand Down Expand Up @@ -66,7 +75,7 @@ Before going further, run the following sample code to check whether the install
>>> assert ort_model.providers == ["ROCMExecutionProvider", "CPUExecutionProvider"]
```

In case this code runs gracefully, congratulations, the installation is successfull! If you encounter the following error or similar,
In case this code runs gracefully, congratulations, the installation is successful! If you encounter the following error or similar,

```
ValueError: Asked to use ROCMExecutionProvider as an ONNX Runtime execution provider, but the available execution providers are ['CPUExecutionProvider'].
Expand Down
Loading