optimize

starvector/serve/conversation.py

@@ -124,7 +124,7 @@ class Conversation:
             try:
                 result = future.result(timeout=0.1)  # Specify the timeout duration in seconds
             except concurrent.futures.TimeoutError:
-                print("Timeout occurred!")
+                # print("Timeout occurred!")
                 result = None
             return result
     

starvector/serve/vllm_api_gradio/gradio_web_server.py

@@ -576,7 +576,7 @@ def build_demo(embed_mode):
                     temperature = gr.Slider(minimum=0.0, maximum=2.0, value=0.2, step=0.05, interactive=True, label="Temperature",)
                     len_penalty = gr.Slider(minimum=0.0, maximum=2.0, value=1.0, step=0.05, interactive=True, label="Length Penalty",)
                     top_p = gr.Slider(minimum=0.0, maximum=1.0, value=0.95, step=0.05, interactive=True, label="Top P",)
-                    max_output_tokens = gr.Slider(minimum=0, maximum=8192, value=8192, step=64, interactive=True, label="Max output tokens",)
+                    max_output_tokens = gr.Slider(minimum=0, maximum=1024, value=1024, step=64, interactive=True, label="Max output tokens",)
 
             with gr.Column(scale=9):
                 with gr.Row():