Update README.md

README.md

@@ -98,7 +98,7 @@ You can refer to the content in [Tencent-Hunyuan-Large](https://github.com/Tence
 
 ### Inference Performance
 
-This section presents the efficiency test results of deploying various models (original and quantized) using vLLM, including inference speed (tokens/s) under different batch sizes.
+This section presents the efficiency test results of deploying various models using vLLM, including inference speed (tokens/s) under different batch sizes.
 
 | Inference Framework | Model      | Number of GPUs (series 1) | input_length | batch=1             | batch=4              |
 |------|------------|-------------------------|-------------------------|---------------------|----------------------|