Update README.md

README.md

@@ -257,3 +257,143 @@ evalplus.evaluate \
   </tbody>
 </table>
 
+
+
+## Inference Performance
+
+
+This model achieves up to 1.9x speedup in single-stream deployment, depending on hardware and use-case scenario.
+The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.6.6.post1, and [GuideLLM](https://github.com/neuralmagic/guidellm).
+
+<details>
+<summary>Benchmarking Command</summary>
+
+```
+guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server
+```
+
+</details>
+
+### Single-stream performance (measured with vLLM version 0.6.6.post1)
+<table>
+  <tr>
+    <td></td>
+    <td></td>
+    <td></td>
+    <th style="text-align: center;" colspan="7" >Latency (s)</th>
+  </tr>
+  <tr>
+    <th>GPU class</th>
+    <th>Model</th>
+    <th>Speedup</th>
+    <th>Code Completion<br>prefill: 256 tokens<br>decode: 1024 tokens</th>
+    <th>Docstring Generation<br>prefill: 768 tokens<br>decode: 128 tokens</th>
+    <th>Code Fixing<br>prefill: 1024 tokens<br>decode: 1024 tokens</th>
+    <th>RAG<br>prefill: 1024 tokens<br>decode: 128 tokens</th>
+    <th>baseion Following<br>prefill: 256 tokens<br>decode: 128 tokens</th>
+    <th>Multi-turn Chat<br>prefill: 512 tokens<br>decode: 256 tokens</th>
+    <th>Large Summarization<br>prefill: 4096 tokens<br>decode: 512 tokens</th>
+  </tr>
+  <tr>
+    <td style="vertical-align: middle;" rowspan="3" >A5000</td>
+    <td>granite-3.1-2b-base</td>
+    <td></td>
+    <td>10.9</td>
+    <td>1.4</td>
+    <td>11.0</td>
+    <td>1.5</td>
+    <td>1.4</td>
+    <td>2.8</td>
+    <td>6.1</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>1.37</td>
+    <td>7.9</td>
+    <td>1.0</td>
+    <td>8.0</td>
+    <td>1.1</td>
+    <td>1.0</td>
+    <td>2.0</td>
+    <td>4.7</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16<br>(this model)</td>
+    <td>1.94</td>
+    <td>5.4</td>
+    <td>0.7</td>
+    <td>5.5</td>
+    <td>0.8</td>
+    <td>0.7</td>
+    <td>1.4</td>
+    <td>3.4</td>
+  </tr>
+  <tr>
+    <td style="vertical-align: middle;" rowspan="3" >A6000</td>
+    <td>granite-3.1-2b-base</td>
+    <td></td>
+    <td>9.8</td>
+    <td>1.3</td>
+    <td>10.0</td>
+    <td>1.3</td>
+    <td>1.3</td>
+    <td>2.6</td>
+    <td>5.4</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>1.31</td>
+    <td>7.8</td>
+    <td>1.0</td>
+    <td>7.6</td>
+    <td>1.0</td>
+    <td>0.9</td>
+    <td>1.9</td>
+    <td>4.5</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16<br>(this model)</td>
+    <td>1.87</td>
+    <td>5.1</td>
+    <td>0.7</td>
+    <td>5.2</td>
+    <td>0.7</td>
+    <td>0.7</td>
+    <td>1.3</td>
+    <td>3.1</td>
+  </tr>
+  <tr>
+    <td style="vertical-align: middle;" rowspan="3" >L40</td>
+    <td>granite-3.1-2b-base</td>
+    <td></td>
+    <td>9.3</td>
+    <td>1.2</td>
+    <td>9.4</td>
+    <td>1.2</td>
+    <td>1.2</td>
+    <td>2.3</td>
+    <td>5.0</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-FP8-dynamic</td>
+    <td>1.26</td>
+    <td>7.3</td>
+    <td>0.9</td>
+    <td>7.4</td>
+    <td>1.0</td>
+    <td>0.9</td>
+    <td>1.8</td>
+    <td>4.1</td>
+  </tr>
+  <tr>
+    <td>granite-3.1-2b-base-quantized.w4a16<br>(this model)</td>
+    <td>1.88</td>
+    <td>4.8</td>
+    <td>0.6</td>
+    <td>4.9</td>
+    <td>0.6</td>
+    <td>0.6</td>
+    <td>1.2</td>
+    <td>2.8</td>
+  </tr>
+</table>