Skip to content

Commit 11f6547

Browse files
spelling mistakes correction, and add short commands for default CUDA EP based olive+modelopt
Signed-off-by: vipandya <vipandya@nvidia.com>
1 parent dd67dfc commit 11f6547

2 files changed

Lines changed: 11 additions & 2 deletions

File tree

docs/source/getting_started/windows/_installation_with_olive.rst

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,9 @@ Setup Steps for Olive with ModelOpt-Windows
2424
$ pip install onnxruntime-genai-cuda
2525
$ pip install onnxruntime-gpu
2626
27-
- Above onnxruntime and onnxruntime-genai packages enable Olive workflow with CUDA Execution-Provider (EP). To use other EPs, install corresponding packages; refer to the ONNX Runtime's `EP documentation <https://onnxruntime.ai/docs/execution-providers/>`_ for details about differfent EPs and thier requirements and installation instructions.
27+
- Above onnxruntime and onnxruntime-genai packages enable Olive workflow with CUDA Execution-Provider (EP). To use other EPs, install corresponding packages.
28+
29+
- Refer to the ONNX Runtime's `EP documentation <https://onnxruntime.ai/docs/execution-providers/>`_ for details about different EPs, their requirements, and installation instructions.
2830

2931
- Additionally, ensure that dependencies for Model Optimizer - Windows are met as mentioned in the :ref:`Install-Page-Standalone-Windows`.
3032

examples/windows/README.md

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,14 @@ pip install nvidia-modelopt[onnx]
5151

5252
### Installation with Olive
5353

54-
The ModelOpt-Windows is integrated in Microsoft's [Olive](https://microsoft.github.io/Olive/) framework. To install ModelOpt with Olive, please refer to the [detailed installation instructions](https://nvidia.github.io/Model-Optimizer/getting_started/windows/_installation_for_Windows.html).
54+
The ModelOpt-Windows is integrated into Microsoft's [Olive](https://microsoft.github.io/Olive/) framework. Run the following commands to install ModelOpt through Olive.
55+
56+
```bash
57+
pip install olive-ai[nvmo]
58+
pip install onnxruntime-genai-cuda
59+
```
60+
61+
For more details, or to use different [ONNX Runtime Execution Providers](https://onnxruntime.ai/docs/execution-providers/), refer to the [detailed installation instructions](https://nvidia.github.io/Model-Optimizer/getting_started/windows/_installation_for_Windows.html).
5562

5663
## Techniques
5764

0 commit comments

Comments
 (0)