Update README.md

README.md

@@ -129,8 +129,8 @@ CogVideoX is an open-source version of the video generation model originating fr
   </tr>
   <tr>
     <td style="text-align: center;">Single GPU VRAM Consumption</td>
-    <td style="text-align: center;">FP16: 18GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>12.5GB* using diffusers</b><br><b>INT8: 7.8GB* using diffusers and torchao</b></td>
-    <td style="text-align: center;">BF16: 26GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>20.7GB* using diffusers</b><br><b>INT8: 11.4GB* using diffusers and torchao</b></td>
+    <td style="text-align: center;">FP16: 18GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>12.5GB* using diffusers</b><br><b>INT8: 7.8GB* using diffusers wtih torchao</b></td>
+    <td style="text-align: center;">BF16: 26GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>20.7GB* using diffusers</b><br><b>INT8: 11.4GB* using diffusers with torchao</b></td>
   </tr>
   <tr>
     <td style="text-align: center;">Multi-GPU Inference VRAM Consumption</td>