Merge pull request #66 from hpcaitech/feature/open_source

Update README.md

README.md

@@ -59,16 +59,16 @@ Here GPT3-12-layers in FP16 is adopted.
 Here a node with 8 A100 80 GB GPUs is adopted. GPUs are fully connected with NvLink.  
 Energon adopts the redundant computation elimination method from [EffectiveTransformer](https://github.com/bytedance/effective_transformer) and the sequence length is set the half of the padding length.
 <div  align="center">    
-    <img src="https://user-images.githubusercontent.com/12018307/168971637-ffd1d6ba-44bb-4043-a275-3dc2a008c048.png" width = "500" height = "200" alt="Architecture" align=center />
+    <img src="https://user-images.githubusercontent.com/12018307/168971637-ffd1d6ba-44bb-4043-a275-3dc2a008c048.png" width = "600" height = "240" alt="Architecture" align=center />
 </div>
 
 #### Latency
 Here GPT3 in FP16 is adopted.  
 Here a node with 8 A100 80 GB GPUs is adopted. Every two GPUs are connected with NvLink.  
 Here the sequence length is set the half of the padding length.  
-FasterTransformer does not support the redundant computation elimination method in distributed execution.
+Here FasterTransformer is adopted in comparison and it does not support the redundant computation elimination method in distributed execution.
 <div  align="center">    
-    <img src="https://user-images.githubusercontent.com/12018307/168971637-ffd1d6ba-44bb-4043-a275-3dc2a008c048.png" width = "500" height = "200" alt="Architecture" align=center />
+    <img src="https://user-images.githubusercontent.com/12018307/168983141-44faad9f-7f44-4296-8be6-63c7f6d76263.png" width = "600" height = "300" alt="Architecture" align=center />
 </div>
 
 ### Contributing