Update README.md

README.md

@@ -117,11 +117,11 @@ Benchmarked on Xiaomi 17 Pro Max.
 <td><p style="text-align: left">GPU</p></td>
 <td><p style="text-align: left">dynamic_int8</p></td>
 <td><p style="text-align: right">1280</p></td>
-<td><p style="text-align: right">- tk/s</p></td>
-<td><p style="text-align: right">- tk/s</p></td>
-<td><p style="text-align: right">- s</p></td>
-<td><p style="text-align: right">- MB</p></td>
-<td><p style="text-align: right">- MB</p></td>
+<td><p style="text-align: right">2,220 tk/s</p></td>
+<td><p style="text-align: right">64 tk/s</p></td>
+<td><p style="text-align: right">0.55 s</p></td>
+<td><p style="text-align: right">813 MB</p></td>
+<td><p style="text-align: right">1103 MB</p></td>
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/FastVLM-0.5B/resolve/main/FastVLM-0.5B.litertlm">&#128279;</a></p></td>
 </tr>
 
@@ -129,11 +129,11 @@ Benchmarked on Xiaomi 17 Pro Max.
 <td><p style="text-align: left">NPU</p></td>
 <td><p style="text-align: left">dynamic_int8</p></td>
 <td><p style="text-align: right">1280</p></td>
-<td><p style="text-align: right">- tk/s</p></td>
-<td><p style="text-align: right">- tk/s</p></td>
-<td><p style="text-align: right">- s</p></td>
-<td><p style="text-align: right">- MB</p></td>
-<td><p style="text-align: right">- MB</p></td>
+<td><p style="text-align: right">11,272 tk/s</p></td>
+<td><p style="text-align: right">106 tk/s</p></td>
+<td><p style="text-align: right">0.12 s</p></td>
+<td><p style="text-align: right">616 MB</p></td>
+<td><p style="text-align: right">899 MB</p></td>
 <td><p style="text-align: left"><a style="text-decoration: none" href="https://huggingface.co/litert-community/FastVLM-0.5B/resolve/main/FastVLM-0.5B.sm8850.litertlm">&#128279;</a></p></td>
 </tr>
 
@@ -143,6 +143,7 @@ Benchmarked on Xiaomi 17 Pro Max.
 
 Notes:
 * Model Size: measured by the size of the file on disk.
+* TTFT includes encoding time for 1 image and corresponding text prompt.
 * Benchmark is run with cache enabled and initialized. During the first run, the latency and memory usage may differ.