Update README.md

README.md

@@ -282,7 +282,7 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
 <summary>Benchmarking Command</summary>
 
 ```
-guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-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
+guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server
 ```
 </details>
 
@@ -327,6 +327,134 @@ guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 --tar
     </tr>
   </thead>
   <tbody style="text-align: center" >
+    <tr>
+      <th rowspan="3" valign="top">A6000</th>
+      <td>4</td>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Llama-70B</th>
+      <td>---</td>
+      <td>7.4</td>
+      <td>152</td>
+      <td>14.9</td>
+      <td>76</td>
+      <td>7.5</td>
+      <td>149</td>
+      <td>7.7</td>
+      <td>146</td>
+      <td>57.2</td>
+      <td>20</td>
+      <td>58.9</td>
+      <td>19</td>
+      <td>31.9</td>
+      <td>35</td>
+      <td>98.4</td>
+      <td>11</td>
+    </tr>
+    <tr>
+      <td>2</td>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8</th>
+      <td>1.93</td>
+      <td>7.7</td>
+      <td>292</td>
+      <td>15.2</td>
+      <td>148</td>
+      <td>7.8</td>
+      <td>287</td>
+      <td>8.0</td>
+      <td>282</td>
+      <td>60.7</td>
+      <td>37</td>
+      <td>60.2</td>
+      <td>37</td>
+      <td>32.3</td>
+      <td>70</td>
+      <td>104.0</td>
+      <td>22</td>
+    </tr>
+    <tr>
+      <td>2</td>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16</th>
+      <td>2.83</td>
+      <td>4.9</td>
+      <td>457</td>
+      <td>10.0</td>
+      <td>225</td>
+      <td>5.5</td>
+      <td>411</td>
+      <td>5.8</td>
+      <td>389</td>
+      <td>38.9</td>
+      <td>58</td>
+      <td>39.2</td>
+      <td>57</td>
+      <td>23.7</td>
+      <td>95</td>
+      <td>76.6</td>
+      <td>29</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">A100</th>
+      <td>2</td>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Llama-70B</th>
+      <td>---</td>
+      <td>6.4</td>
+      <td>157</td>
+      <td>12.8</td>
+      <td>79</td>
+      <td>6.6</td>
+      <td>153</td>
+      <td>6.7</td>
+      <td>151</td>
+      <td>50.4</td>
+      <td>20</td>
+      <td>50.8</td>
+      <td>20</td>
+      <td>27.0</td>
+      <td>37</td>
+      <td>85.4</td>
+      <td>12</td>
+    </tr>
+    <tr>
+      <td>2</td>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8</th>
+      <td>1.48</td>
+      <td>4.1</td>
+      <td>245</td>
+      <td>8.2</td>
+      <td>123</td>
+      <td>4.2</td>
+      <td>238</td>
+      <td>4.3</td>
+      <td>235</td>
+      <td>32.4</td>
+      <td>31</td>
+      <td>32.8</td>
+      <td>31</td>
+      <td>17.6</td>
+      <td>57</td>
+      <td>90.8</td>
+      <td>11</td>
+    </tr>
+    <tr>
+      <td>1</td>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16</th>
+      <td>2.69</td>
+      <td>4.6</td>
+      <td>440</td>
+      <td>9.2</td>
+      <td>220</td>
+      <td>4.9</td>
+      <td>407</td>
+      <td>5.2</td>
+      <td>389</td>
+      <td>35.3</td>
+      <td>57</td>
+      <td>36.3</td>
+      <td>55</td>
+      <td>21.2</td>
+      <td>95</td>
+      <td>68.1</td>
+      <td>30</td>
+    </tr>
     <tr>
       <th rowspan="3" valign="top">H100</th>
       <td>2</td>
@@ -438,6 +566,128 @@ guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 --tar
     </tr>
   </thead>
   <tbody style="text-align: center" >
+    <tr>
+      <th rowspan="3" valign="top">A6000x4</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Llama-70B</th>
+      <td>---</td>
+      <td>3.65</td>
+      <td>4102</td>
+      <td>1.56</td>
+      <td>1757</td>
+      <td>1.90</td>
+      <td>2143</td>
+      <td>1.48</td>
+      <td>1665</td>
+      <td>0.44</td>
+      <td>493</td>
+      <td>0.34</td>
+      <td>380</td>
+      <td>0.22</td>
+      <td>245</td>
+      <td>0.05</td>
+      <td>55</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8</th>
+      <td>1.76</td>
+      <td>5.89</td>
+      <td>6625</td>
+      <td>2.94</td>
+      <td>3307</td>
+      <td>3.36</td>
+      <td>3775</td>
+      <td>2.59</td>
+      <td>2916</td>
+      <td>0.74</td>
+      <td>828</td>
+      <td>0.53</td>
+      <td>601</td>
+      <td>0.35</td>
+      <td>398</td>
+      <td>0.11</td>
+      <td>120</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16</th>
+      <td>1.48</td>
+      <td>4.91</td>
+      <td>5528</td>
+      <td>2.01</td>
+      <td>2259</td>
+      <td>2.03</td>
+      <td>2280</td>
+      <td>1.12</td>
+      <td>1255</td>
+      <td>1.11</td>
+      <td>1251</td>
+      <td>0.76</td>
+      <td>852</td>
+      <td>0.24</td>
+      <td>267</td>
+      <td>0.07</td>
+      <td>81</td>
+    </tr>
+    <tr>
+      <th rowspan="3" valign="top">A100x4</th>
+      <th>deepseek-ai/DeepSeek-R1-Distill-Llama-70B</th>
+      <td>---</td>
+      <td>10.41</td>
+      <td>5235</td>
+      <td>5.10</td>
+      <td>2565</td>
+      <td>5.50</td>
+      <td>2766</td>
+      <td>4.36</td>
+      <td>2193</td>
+      <td>1.49</td>
+      <td>751</td>
+      <td>1.21</td>
+      <td>607</td>
+      <td>0.89</td>
+      <td>447</td>
+      <td>0.19</td>
+      <td>98</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8</th>
+      <td>1.63</td>
+      <td>18.11</td>
+      <td>9103</td>
+      <td>8.90</td>
+      <td>4477</td>
+      <td>9.41</td>
+      <td>4730</td>
+      <td>7.42</td>
+      <td>3731</td>
+      <td>2.44</td>
+      <td>1229</td>
+      <td>1.89</td>
+      <td>948</td>
+      <td>1.26</td>
+      <td>631</td>
+      <td>0.30</td>
+      <td>149</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16</th>
+      <td>1.12</td>
+      <td>12.63</td>
+      <td>6353</td>
+      <td>5.32</td>
+      <td>2673</td>
+      <td>5.58</td>
+      <td>2804</td>
+      <td>4.27</td>
+      <td>2144</td>
+      <td>2.30</td>
+      <td>1158</td>
+      <td>1.45</td>
+      <td>729</td>
+      <td>0.76</td>
+      <td>381</td>
+      <td>0.22</td>
+      <td>110</td>
+    </tr>
     <tr>
       <th rowspan="3" valign="top">H100x4</th>
       <th>deepseek-ai/DeepSeek-R1-Distill-Llama-70B</th>
@@ -506,4 +756,5 @@ guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 --tar
 
 **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).
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
+