remove

Author: echarlaix

docs/source/inference.mdx

@@ -108,14 +108,6 @@ optimum-cli export openvino --model gpt2 --weight-format int8 ov_model
 This type of optimization allows to reduce the memory footprint and inference latency.
 
 
-| `--weight-format` |
-|-------------------|
-| `fp32`            |
-| `fp16`            |
-| `int8`            |
-| `int4`            |
-
-
 By default the quantization scheme will be [assymmetric](https://github.com/openvinotoolkit/nncf/blob/develop/docs/compression_algorithms/Quantization.md#asymmetric-quantization), to make it [symmetric](https://github.com/openvinotoolkit/nncf/blob/develop/docs/compression_algorithms/Quantization.md#symmetric-quantization) you can add `--sym`.
 
 For INT4 quantization you can also specify the following arguments :