Remove "Maximum UI updates/second" parameter (#5507)

modules/shared.py

@@ -46,7 +46,6 @@ settings = {
     'truncation_length_min': 0,
     'truncation_length_max': 200000,
     'max_tokens_second': 0,
-    'max_updates_second': 0,
     'prompt_lookup_num_tokens': 0,
     'custom_stopping_strings': '',
     'custom_token_bans': '',

modules/text_generation.py

@@ -80,19 +80,16 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
         state = copy.deepcopy(state)
         state['stream'] = True
 
-    min_update_interval = 0
-    if state.get('max_updates_second', 0) > 0:
-        min_update_interval = 1 / state['max_updates_second']
-
     # Generate
     for reply in generate_func(question, original_question, seed, state, stopping_strings, is_chat=is_chat):
         reply, stop_found = apply_stopping_strings(reply, all_stop_strings)
         if escape_html:
             reply = html.escape(reply)
+
         if is_stream:
             cur_time = time.time()
 
-            # Maximum number of tokens/second
+            # Limit number of tokens/second to make text readable in real time
             if state['max_tokens_second'] > 0:
                 diff = 1 / state['max_tokens_second'] - (cur_time - last_update)
                 if diff > 0:
@@ -100,13 +97,8 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
 
                 last_update = time.time()
                 yield reply
-
-            # Limit updates to avoid lag in the Gradio UI
-            # API updates are not limited
             else:
-                if cur_time - last_update > min_update_interval:
+                yield reply
-                    last_update = cur_time
-                    yield reply
 
         if stop_found or (state['max_tokens_second'] > 0 and shared.stop_everything):
             break

modules/ui.py

@@ -112,7 +112,6 @@ def list_interface_input_elements():
         'max_new_tokens',
         'auto_max_new_tokens',
         'max_tokens_second',
-        'max_updates_second',
         'prompt_lookup_num_tokens',
         'seed',
         'temperature',

modules/ui_parameters.py

@@ -72,7 +72,6 @@ def create_ui(default_preset):
                         with gr.Column():
                             shared.gradio['truncation_length'] = gr.Slider(value=get_truncation_length(), minimum=shared.settings['truncation_length_min'], maximum=shared.settings['truncation_length_max'], step=256, label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
                             shared.gradio['max_tokens_second'] = gr.Slider(value=shared.settings['max_tokens_second'], minimum=0, maximum=20, step=1, label='Maximum tokens/second', info='To make text readable in real time.')
-                            shared.gradio['max_updates_second'] = gr.Slider(value=shared.settings['max_updates_second'], minimum=0, maximum=24, step=1, label='Maximum UI updates/second', info='Set this if you experience lag in the UI during streaming.')
                             shared.gradio['prompt_lookup_num_tokens'] = gr.Slider(value=shared.settings['prompt_lookup_num_tokens'], minimum=0, maximum=10, step=1, label='prompt_lookup_num_tokens', info='Activates Prompt Lookup Decoding.')
 
                             shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=1, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='In addition to the defaults. Written between "" and separated by commas.', placeholder='"\\n", "\\nYou:"')

settings-template.yaml

@@ -15,7 +15,6 @@ truncation_length: 2048
 truncation_length_min: 0
 truncation_length_max: 200000
 max_tokens_second: 0
-max_updates_second: 0
 prompt_lookup_num_tokens: 0
 custom_stopping_strings: ''
 custom_token_bans: ''