We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 94a351e commit 4f8ca40Copy full SHA for 4f8ca40
examples/openvino/README.md
@@ -57,12 +57,6 @@ python aot_openvino_compiler.py --suite <MODEL_SUITE> --model <MODEL_NAME> --inp
57
- **`--quantize`** (optional):
58
Enable model quantization. --dataset argument is requred for the quantization. `huggingface` suite does not supported yet.
59
60
-- **`--quantization_flow`** (optional):
61
- Specifies the way to quantize torch.fx.GraphModule.
62
- Supported values:
63
- - `nncf`: `nncf quantize_pt2e` API (default)
64
- - `pt2e`: torch ao quantization pipeline.
65
-
66
- **`--validate`** (optional):
67
Enable model validation. --dataset argument is requred for the validation. `huggingface` suite does not supported yet.
68
0 commit comments