Update README.md
Browse files
README.md
CHANGED
|
@@ -59,6 +59,7 @@ huggingface-cli download onnxruntime/Gemma-3-ONNX --include {model_name}/cpu_and
|
|
| 59 |
pip install --pre onnxruntime-genai
|
| 60 |
|
| 61 |
# Please adjust the model directory (-m) accordingly
|
|
|
|
| 62 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 63 |
python model-mm.py -m {model_name}/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4 -e cpu
|
| 64 |
```
|
|
@@ -74,6 +75,7 @@ huggingface-cli download onnxruntime/Gemma-3-ONNX --include {model_name}/gpu/cud
|
|
| 74 |
pip install --pre onnxruntime-genai-cuda
|
| 75 |
|
| 76 |
# Please adjust the model directory (-m) accordingly
|
|
|
|
| 77 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 78 |
python model-mm.py -m {model_name}/gpu/cuda-bf16-io-int4-rtn-block-32/ -e cuda
|
| 79 |
```
|
|
@@ -89,6 +91,7 @@ huggingface-cli download onnxruntime/Gemma-3-ONNX --include {model_name}/gpu/gpu
|
|
| 89 |
pip install --pre onnxruntime-genai-directml
|
| 90 |
|
| 91 |
# Please adjust the model directory (-m) accordingly
|
|
|
|
| 92 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 93 |
python model-mm.py -m {model_name}/gpu/gpu-fp16-io-int4-rtn-block-32/ -e dml
|
| 94 |
```
|
|
|
|
| 59 |
pip install --pre onnxruntime-genai
|
| 60 |
|
| 61 |
# Please adjust the model directory (-m) accordingly
|
| 62 |
+
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
|
| 63 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 64 |
python model-mm.py -m {model_name}/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4 -e cpu
|
| 65 |
```
|
|
|
|
| 75 |
pip install --pre onnxruntime-genai-cuda
|
| 76 |
|
| 77 |
# Please adjust the model directory (-m) accordingly
|
| 78 |
+
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
|
| 79 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 80 |
python model-mm.py -m {model_name}/gpu/cuda-bf16-io-int4-rtn-block-32/ -e cuda
|
| 81 |
```
|
|
|
|
| 91 |
pip install --pre onnxruntime-genai-directml
|
| 92 |
|
| 93 |
# Please adjust the model directory (-m) accordingly
|
| 94 |
+
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
|
| 95 |
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
|
| 96 |
python model-mm.py -m {model_name}/gpu/gpu-fp16-io-int4-rtn-block-32/ -e dml
|
| 97 |
```
|