Update README.md

README.md

@@ -275,7 +275,7 @@ lm_eval \
 ## Inference Performance
 
 
-This model achieves up to 2.80x speedup in single-stream deployment and up to 1.70x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
+This model achieves up to 2.80x speedup in single-stream deployment and up to 1.75x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 
 <details>
@@ -427,21 +427,21 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     <tr>
       <td>neuralmagic/Pixtral-Large-Instruct-2411-hf-quantized.w8a8</td>
       <td>1.70</td>
-      <td>1.6</td>
+      <td>0.8</td>
       <td>766</td>
-      <td>2.2</td>
+      <td>1.1</td>
       <td>1142</td>
-      <td>2.6</td>
+      <td>1.3</td>
       <td>1348</td>
     </tr>
     <tr>
       <td>neuralmagic/Pixtral-Large-Instruct-2411-hf-quantized.w4a16</td>
       <td>1.48</td>
-      <td>1.0</td>
+      <td>0.5</td>
       <td>552</td>
-      <td>2.0</td>
+      <td>1.0</td>
       <td>1010</td>
-      <td>2.8</td>
+      <td>1.4</td>
       <td>1360</td>
     </tr>
     <tr>
@@ -458,21 +458,21 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     <tr>
       <td>neuralmagic/Pixtral-Large-Instruct-2411-hf-FP8-Dynamic</td>
       <td>1.61</td>
-      <td>3.4</td>
+      <td>1.7</td>
       <td>905</td>
-      <td>5.2</td>
+      <td>2.6</td>
       <td>1406</td>
-      <td>6.4</td>
+      <td>3.2</td>
       <td>1759</td>
     </tr>
     <tr>
       <td>neuralmagic/Pixtral-Large-Instruct-2411-hf-quantized.w4a16</td>
       <td>1.33</td>
-      <td>2.8</td>
+      <td>1.4</td>
       <td>761</td>
-      <td>4.4</td>
+      <td>2.2</td>
       <td>1228</td>
-      <td>5.4</td>
+      <td>2.7</td>
       <td>1480</td>
     </tr>
   </tbody>