Update README.md

README.md

@@ -276,3 +276,478 @@ lm_eval \
     </tr>
   </tbody>
 </table>
+
+## Inference Performance
+
+
+This model achieves up to 2.8x speedup in single-stream deployment and up to 1.4x 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>
+<summary>Benchmarking Command</summary>
+
+```
+guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-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 0.7.2)
+<table>
+  <thead>
+    <tr>
+      <th></th>
+      <th></th>
+      <th></th>
+      <th style="text-align: center;" colspan="2" >Instruction Following<br>256 / 128</th>
+      <th style="text-align: center;" colspan="2" >Multi-turn Chat<br>512 / 256</th>
+      <th style="text-align: center;" colspan="2" >Docstring Generation<br>768 / 128</th>
+      <th style="text-align: center;" colspan="2" >RAG<br>1024 / 128</th>
+      <th style="text-align: center;" colspan="2" >Code Completion<br>256 / 1024</th>
+      <th style="text-align: center;" colspan="2" >Code Fixing<br>1024 / 1024</th>
+      <th style="text-align: center;" colspan="2" >Large Summarization<br>4096 / 512</th>
+      <th style="text-align: center;" colspan="2" >Large RAG<br>10240 / 1536</th>
+    </tr>
+    <tr>
+      <th>Hardware</th>
+      <th>Model</th>
+      <th>Average cost reduction</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+      <th>Latency (s)</th>
+      <th>QPD</th>
+    </tr>
+  </thead>
+  <tbody style="text-align: center" >
+    <tr>
+      <th rowspan="3" valign="top">A6000x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>5.4</td>
+      <td>837</td>
+      <td>10.7</td>
+      <td>419</td>
+      <td>5.5</td>
+      <td>813</td>
+      <td>5.6</td>
+      <td>805</td>
+      <td>42.2</td>
+      <td>107</td>
+      <td>42.8</td>
+      <td>105</td>
+      <td>22.9</td>
+      <td>197</td>
+      <td>71.7</td>
+      <td>63</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w8a8</th>
+      <td>1.59</td>
+      <td>3.3</td>
+      <td>1345</td>
+      <td>6.7</td>
+      <td>673</td>
+      <td>3.4</td>
+      <td>1315</td>
+      <td>3.5</td>
+      <td>1296</td>
+      <td>26.5</td>
+      <td>170</td>
+      <td>26.8</td>
+      <td>168</td>
+      <td>14.5</td>
+      <td>310</td>
+      <td>48.3</td>
+      <td>93</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>2.51</td>
+      <td>2.0</td>
+      <td>2275</td>
+      <td>4.0</td>
+      <td>1127</td>
+      <td>2.2</td>
+      <td>2072</td>
+      <td>2.3</td>
+      <td>1945</td>
+      <td>15.3</td>
+      <td>294</td>
+      <td>15.9</td>
+      <td>283</td>
+      <td>9.9</td>
+      <td>456</td>
+      <td>36.6</td>
+      <td>123</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">A100x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>2.6</td>
+      <td>765</td>
+      <td>5.2</td>
+      <td>383</td>
+      <td>2.7</td>
+      <td>746</td>
+      <td>2.7</td>
+      <td>732</td>
+      <td>20.8</td>
+      <td>97</td>
+      <td>21.2</td>
+      <td>95</td>
+      <td>11.3</td>
+      <td>179</td>
+      <td>36.7</td>
+      <td>55</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w8a8</th>
+      <td>1.34</td>
+      <td>1.9</td>
+      <td>1072</td>
+      <td>3.8</td>
+      <td>533</td>
+      <td>1.9</td>
+      <td>1045</td>
+      <td>1.9</td>
+      <td>1032</td>
+      <td>14.8</td>
+      <td>136</td>
+      <td>15.2</td>
+      <td>132</td>
+      <td>8.1</td>
+      <td>248</td>
+      <td>39.6</td>
+      <td>51</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>1.93</td>
+      <td>1.2</td>
+      <td>1627</td>
+      <td>2.5</td>
+      <td>810</td>
+      <td>1.3</td>
+      <td>1530</td>
+      <td>1.4</td>
+      <td>1474</td>
+      <td>9.7</td>
+      <td>208</td>
+      <td>10.2</td>
+      <td>197</td>
+      <td>5.8</td>
+      <td>348</td>
+      <td>37.6</td>
+      <td>53</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">H100x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>1.6</td>
+      <td>672</td>
+      <td>3.3</td>
+      <td>334</td>
+      <td>1.7</td>
+      <td>662</td>
+      <td>1.7</td>
+      <td>652</td>
+      <td>12.8</td>
+      <td>85</td>
+      <td>13.0</td>
+      <td>84</td>
+      <td>7.0</td>
+      <td>155</td>
+      <td>25.2</td>
+      <td>43</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-FP8-dynamic</th>
+      <td>1.33</td>
+      <td>1.2</td>
+      <td>925</td>
+      <td>2.3</td>
+      <td>467</td>
+      <td>1.2</td>
+      <td>908</td>
+      <td>1.2</td>
+      <td>896</td>
+      <td>9.3</td>
+      <td>118</td>
+      <td>9.5</td>
+      <td>115</td>
+      <td>5.2</td>
+      <td>210</td>
+      <td>23.9</td>
+      <td>46</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>1.37</td>
+      <td>1.2</td>
+      <td>944</td>
+      <td>2.3</td>
+      <td>474</td>
+      <td>1.2</td>
+      <td>931</td>
+      <td>1.2</td>
+      <td>907</td>
+      <td>9.1</td>
+      <td>121</td>
+      <td>9.2</td>
+      <td>119</td>
+      <td>5.1</td>
+      <td>214</td>
+      <td>22.5</td>
+      <td>49</td>
+    </tr>
+  </tbody>
+</table>
+
+**Use case profiles: prompt tokens / generation tokens
+
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
+
+
+### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
+<table>
+  <thead>
+    <tr>
+      <th></th>
+      <th></th>
+      <th></th>
+      <th style="text-align: center;" colspan="2" >Instruction Following<br>256 / 128</th>
+      <th style="text-align: center;" colspan="2" >Multi-turn Chat<br>512 / 256</th>
+      <th style="text-align: center;" colspan="2" >Docstring Generation<br>768 / 128</th>
+      <th style="text-align: center;" colspan="2" >RAG<br>1024 / 128</th>
+      <th style="text-align: center;" colspan="2" >Code Completion<br>256 / 1024</th>
+      <th style="text-align: center;" colspan="2" >Code Fixing<br>1024 / 1024</th>
+      <th style="text-align: center;" colspan="2" >Large Summarization<br>4096 / 512</th>
+      <th style="text-align: center;" colspan="2" >Large RAG<br>10240 / 1536</th>
+    </tr>
+    <tr>
+      <th>Hardware</th>
+      <th>Model</th>
+      <th>Average cost reduction</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+      <th>Maximum throughput (QPS)</th>
+      <th>QPD</th>
+    </tr>
+  </thead>
+  <tbody style="text-align: center" >
+    <tr>
+      <th rowspan="3" valign="top">A6000x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>13.7</td>
+      <td>30785</td>
+      <td>5.5</td>
+      <td>12327</td>
+      <td>6.5</td>
+      <td>14517</td>
+      <td>5.1</td>
+      <td>11439</td>
+      <td>2.0</td>
+      <td>4434</td>
+      <td>1.3</td>
+      <td>2982</td>
+      <td>0.6</td>
+      <td>1462</td>
+      <td>0.2</td>
+      <td>371</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w8a8</th>
+      <td>1.44</td>
+      <td>21.4</td>
+      <td>48181</td>
+      <td>8.2</td>
+      <td>18421</td>
+      <td>9.8</td>
+      <td>22051</td>
+      <td>7.8</td>
+      <td>17462</td>
+      <td>2.8</td>
+      <td>6281</td>
+      <td>1.7</td>
+      <td>3758</td>
+      <td>1.0</td>
+      <td>2335</td>
+      <td>0.2</td>
+      <td>419</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>0.98</td>
+      <td>12.7</td>
+      <td>28540</td>
+      <td>5.7</td>
+      <td>12796</td>
+      <td>5.4</td>
+      <td>12218</td>
+      <td>3.7</td>
+      <td>8401</td>
+      <td>2.5</td>
+      <td>5583</td>
+      <td>1.3</td>
+      <td>2987</td>
+      <td>0.7</td>
+      <td>1489</td>
+      <td>0.2</td>
+      <td>368</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">A100x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>15.6</td>
+      <td>31306</td>
+      <td>7.1</td>
+      <td>14192</td>
+      <td>7.7</td>
+      <td>15435</td>
+      <td>6.0</td>
+      <td>11971</td>
+      <td>2.4</td>
+      <td>4878</td>
+      <td>1.6</td>
+      <td>3298</td>
+      <td>0.9</td>
+      <td>1862</td>
+      <td>0.2</td>
+      <td>355</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w8a8</th>
+      <td>1.31</td>
+      <td>20.8</td>
+      <td>41907</td>
+      <td>9.3</td>
+      <td>18724</td>
+      <td>10.5</td>
+      <td>21043</td>
+      <td>8.4</td>
+      <td>16886</td>
+      <td>3.0</td>
+      <td>5975</td>
+      <td>1.9</td>
+      <td>3917</td>
+      <td>1.2</td>
+      <td>2481</td>
+      <td>0.2</td>
+      <td>464</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>0.94</td>
+      <td>14.0</td>
+      <td>28146</td>
+      <td>6.5</td>
+      <td>13042</td>
+      <td>6.5</td>
+      <td>12987</td>
+      <td>5.1</td>
+      <td>10194</td>
+      <td>2.6</td>
+      <td>5269</td>
+      <td>1.5</td>
+      <td>2925</td>
+      <td>0.9</td>
+      <td>1849</td>
+      <td>0.2</td>
+      <td>382</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">H100x1</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</th>
+      <td>---</td>
+      <td>31.4</td>
+      <td>34404</td>
+      <td>14.1</td>
+      <td>15482</td>
+      <td>16.6</td>
+      <td>18149</td>
+      <td>13.3</td>
+      <td>14572</td>
+      <td>4.7</td>
+      <td>5099</td>
+      <td>2.6</td>
+      <td>2849</td>
+      <td>1.9</td>
+      <td>2060</td>
+      <td>0.3</td>
+      <td>347</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-FP8-dynamic</th>
+      <td>1.31</td>
+      <td>40.9</td>
+      <td>44729</td>
+      <td>18.5</td>
+      <td>20260</td>
+      <td>22.1</td>
+      <td>24165</td>
+      <td>18.1</td>
+      <td>19779</td>
+      <td>5.7</td>
+      <td>6246</td>
+      <td>3.4</td>
+      <td>3681</td>
+      <td>2.5</td>
+      <td>2746</td>
+      <td>0.4</td>
+      <td>474</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16</th>
+      <td>1.12</td>
+      <td>33.3</td>
+      <td>36387</td>
+      <td>15.0</td>
+      <td>16453</td>
+      <td>17.6</td>
+      <td>19241</td>
+      <td>14.2</td>
+      <td>15576</td>
+      <td>4.6</td>
+      <td>5034</td>
+      <td>3.0</td>
+      <td>3292</td>
+      <td>2.2</td>
+      <td>2412</td>
+      <td>0.4</td>
+      <td>481</td>
+    </tr>
+  </tbody>
+</table>
+
+**Use case profiles: prompt tokens / generation tokens
+
+**QPS: Queries per second.
+
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).