added async to bot_comms and llama_generation

app.py

@@ -79,10 +79,10 @@ def gpt_generation(input: str,
 
 # Place just input pass and return generation output
 @spaces.GPU(duration=120)
-def llama_generation(input_text: str,
-                     history: list,
-                     temperature: float,
-                     max_new_tokens: int):
+async def llama_generation(input_text: str,
+                           history: list,
+                           temperature: float,
+                           max_new_tokens: int):
     """
     Pass input texts, tokenize, output and back to text.
     """
@@ -130,10 +130,10 @@ def check_cuda():
 first_time = True
 llm_mode = ""
 
-def bot_comms(input_text: str,
-              history: list,
-              temperature: float,
-              max_new_tokens: int):
+async def bot_comms(input_text: str,
+                    history: list,
+                    temperature: float,
+                    max_new_tokens: int):
     """
     The connection between gradio and the LLM's
     """