Chat is a coroutine.

app.py

@@ -196,6 +196,11 @@ def chat(
         if '\ufffd' not in tmp:
             print(tmp, end='', flush=True)
             out_last = begin + i + 1
+            out_str += tmp
+
+            chatbot[-1][1] = out_str.strip()
+            history = [state, all_tokens]
+            yield chatbot, history
 
         out_str = pipeline.decode(all_tokens[begin:])
         out_str = out_str.replace("\r\n", '\n').replace('\\n', '\n')
@@ -208,7 +213,7 @@ def chat(
 
     chatbot[-1][1] = out_str.strip()
     history = [state, all_tokens]
-    return chatbot, history
+    yield chatbot, history
 
 with gr.Blocks(title=title) as demo:
     with gr.Tab("Generative"):
@@ -264,7 +269,7 @@ with gr.Blocks(title=title) as demo:
         chat_outputs = [chatbot, state]
         message.submit(user, [message, chatbot], [message, chatbot], queue=False).then(chat, chat_inputs, chat_outputs)
         send.click(user, [message, chatbot], [message, chatbot], queue=False).then(chat, chat_inputs, chat_outputs)
-        clear.click(lambda: ([], None, ""), [], [chatbot, state, message])
+        clear.click(lambda: ([], None, ""), [], [chatbot, state, message], queue=False)
 
 demo.queue(max_size=10)
 demo.launch(share=False)