Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-25 13:58:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

UI: add "Maximum UI updates/second" parameter

Browse Source
This commit is contained in:
oobabooga 2023-12-24 09:17:40 -08:00
parent 1b8b61b928
commit 8c60495878
4 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/shared.py
View File

@ -45,6 +45,7 @@ settings = {
'truncation_length_min': 0,
'truncation_length_max': 200000,
'max_tokens_second': 0,
'max_updates_second': 0,
'custom_stopping_strings': '',
'custom_token_bans': '',
'auto_max_new_tokens': False,

7
modules/text_generation.py
View File

@ -77,6 +77,10 @@ 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)
@ -94,10 +98,9 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
last_update = time.time()
yield reply
# Limit updates to 24 or 5 per second to avoid lag in the Gradio UI
# Limit updates to avoid lag in the Gradio UI
# API updates are not limited
else:
min_update_interval = 0 if not for_ui else 0.2 if (shared.args.listen or shared.args.share) else 0.0417
if cur_time - last_update > min_update_interval:
last_update = cur_time
yield reply

1
modules/ui.py
View File

@ -110,6 +110,7 @@ def list_interface_input_elements():
'max_new_tokens',
'auto_max_new_tokens',
'max_tokens_second',
'max_updates_second',
'seed',
'temperature',
'temperature_last',

4
modules/ui_parameters.py
View File

@ -66,7 +66,9 @@ def create_ui(default_preset):
with gr.Row():
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 number of tokens/second', info='To make text readable in real time.')
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=20, step=1, label='Maximum UI updates/second', info='Set this if you experience lag in the UI during streaming.')
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:"')
shared.gradio['custom_token_bans'] = gr.Textbox(value=shared.settings['custom_token_bans'] or None, label='Custom token bans', info='Specific token IDs to ban from generating, comma-separated. The IDs can be found in the Default or Notebook tab.')