Install ONNX Runtime for ROCm

ONNX Runtime accelerates machine learning inference using the AMD MIGraphX execution provider on ROCm-supported GPUs.

ROCm version

10.1.0

10.0.0

7.14.1

7.14.0

Installation method

pip

Prerequisites

ONNX Runtime 1.29.0 is currently supported on:

• gfx950 AMD Instinct MI355X, MI350X, and MI350P

• gfx942 AMD Instinct MI325X, MI300X, and MI300A

• gfx90a AMD Instinct MI250X, MI250, and MI210

• gfx1200, gfx1201, gfx1100, gfx1101, and gfx1102 Radeon GPUs.

• gfx1153, gfx1152, gfx1151, and gfx1150 Ryzen AI processors.

See the ROCm compatibility matrix for more information.

• Ensure your system has Python 3.12 installed and accessible.

ONNX Runtime is currently supported on:

• gfx950 AMD Instinct MI355X and MI350X

• gfx942 AMD Instinct MI325X and MI300X

• gfx1200, gfx1201, gfx1100, gfx1101, and gfx1102 Radeon GPUs.

See the ROCm compatibility matrix for more information.

• Ensure your system has Python 3.14 or 3.12 installed and accessible.

ONNX Runtime is currently supported on gfx950 AMD Instinct MI355X and MI350X data center GPUs and gfx942 MI325X and MI300X GPUs. See the ROCm compatibility matrix (ROCm 7.14.1) for more information.

• Ensure your system has Python 3.12 installed and accessible.

ONNX Runtime is currently supported on gfx950 AMD Instinct MI355X and MI350X data center GPUs and gfx942 MI325X and MI300X GPUs. See the ROCm compatibility matrix (ROCm 7.14.0) for more information.

• Ensure your system has Python 3.12 installed and accessible.

Install ONNX Runtime on Linux

ONNX Runtime requires ROCm to be installed on your system first.

Install ROCm

For instructions, see Install AMD ROCm. Use the selector panel on that page to view instructions appropriate for your system environment.

For instructions, see Install AMD ROCm. Use the selector panel on that page to view instructions appropriate for your system environment.

For instructions, see Install AMD ROCm 7.14.1. Use the selector panel on that page to view instructions appropriate for your system environment.

For instructions, see Install AMD ROCm 7.14.0. Use the selector panel on that page to view instructions appropriate for your system environment.

Install ONNX Runtime using pip

1. Create and activate a virtual environment or activate an existing ROCm 10.1.0 environment.

   Python 3.12

   python3.12 -m venv .venv
   source .venv/bin/activate
   

2. Install MIGraphX using pip. See Install MIGraphX for installation instructions.

   Important

   MIGraphX must be installed using pip. The onnxruntime-ep-migraphx wheel declares a dependency on migraphx-libs, which is only available from the MIGraphX pip repository. Installing MIGraphX using the package manager or tarball method doesn’t satisfy this dependency, and installing the execution provider in the next step fails to resolve.

3. Install ONNX Runtime and the onnxruntime-ep-migraphx execution provider plugin.

   python -m pip install --extra-index-url https://stable.repo.amd.com/rocm/onnxruntime/whl-next/ "onnxruntime-ep-migraphx==1.0.0+rocm10.1.0"
   

4. Confirm ONNX Runtime is correctly installed and the MIGraphX execution provider is available.

   The EP plugin must be explicitly registered using onnxruntime_ep_migraphx before querying available providers.

   python -c "import onnxruntime as ort, onnxruntime_ep_migraphx as m; [ort.register_execution_provider_library(n,p) for n,p in zip(m.get_ep_names(), m.get_library_paths())]; print(ort.get_available_providers())"
   

   You should see MIGraphXExecutionProvider in the output:

   ['CPUExecutionProvider', 'MIGraphXExecutionProvider']
   

1. Create and activate a virtual environment or activate an existing ROCm 10.0.0 environment.

   Python 3.14

   python3.14 -m venv .venv
   source .venv/bin/activate
   

   Python 3.12

   python3.12 -m venv .venv
   source .venv/bin/activate
   

2. Install MIGraphX using pip. See Install MIGraphX for installation instructions.

3. Install ONNX Runtime and the onnxruntime-ep-migraphx execution provider plugin.

   python -m pip install --extra-index-url https://stable.repo.amd.com/rocm/onnxruntime/whl-next/ "onnxruntime-ep-migraphx==1.0.0+rocm10.0.0"
   

4. As a workaround due to packaging issues, create the required soname symlink and set library search paths. For example, if you installed MIGraphX using pip:

   SP=$(python -c "import site; print(site.getsitepackages()[0])")
   ln -sf $SP/onnxruntime/capi/libonnxruntime.so.1.29.0 $SP/onnxruntime/capi/libonnxruntime.so.1
   export LD_LIBRARY_PATH=$SP/onnxruntime/capi:$SP/migraphx_libs:$LD_LIBRARY_PATH
   

   Tip

   The symlink only needs to be created once. For persistence, LD_LIBRARY_PATH should be set for each shell session or added to your shell startup script (e.g. ~/.bashrc).

5. Confirm ONNX Runtime is correctly installed and the MIGraphX execution provider is available.

   The EP plugin must be explicitly registered using onnxruntime_ep_migraphx before querying available providers. migraphx must be imported first to initialize the ROCm runtime.

   python -c "import migraphx, onnxruntime as ort, onnxruntime_ep_migraphx as m; [ort.register_execution_provider_library(n,p) for n,p in zip(m.get_ep_names(), m.get_library_paths())]; print(ort.get_available_providers())"
   

   You should see MIGraphXExecutionProvider in the output:

   ['CPUExecutionProvider', 'MIGraphXExecutionProvider']
   

1. Create and activate a virtual environment or activate an existing ROCm 7.14.1 environment. To create a new Python 3.12 virtual environment:

   python3.12 -m venv .venv
   source .venv/bin/activate
   

2. Download and install the wheels.

   python -m pip install https://rocm.frameworks.amd.com/whl-multi-arch/onnxruntime-migraphx/onnxruntime_migraphx-1.23.2%2Brocm7.14.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
   

1. Create and activate a virtual environment or activate an existing ROCm 7.14.0 environment. To create a new Python 3.12 virtual environment:

   python3.12 -m venv .venv
   source .venv/bin/activate
   

2. Download and install the wheels.

   python -m pip install https://rocm.frameworks.amd.com/whl-multi-arch/onnxruntime-migraphx/onnxruntime_migraphx-1.23.2%2Brocm7.14.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
   

See also

See MIGraphX Execution Provider (ONNX Runtime docs) for more information.