AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add back the max_updates_second parameter (#5937)

Browse Source
This commit is contained in:
oobabooga 2024-04-26 10:14:51 -03:00 committed by GitHub
parent 6761b5e7c6
commit 70845c76fb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/shared.py
View File

@ -46,6 +46,7 @@ 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': '',

11
modules/text_generation.py
View File

@ -84,6 +84,10 @@ 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)
@ -101,7 +105,14 @@ 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:
last_update = cur_time
yield reply
yield reply
if stop_found or (state['max_tokens_second'] > 0 and shared.stop_everything):

1
modules/ui.py
View File

@ -122,6 +122,7 @@ def list_interface_input_elements():
'max_new_tokens',
'auto_max_new_tokens',
'max_tokens_second',
'max_updates_second',
'prompt_lookup_num_tokens',
'seed',
'temperature',

1
modules/ui_parameters.py
View File

@ -85,6 +85,7 @@ def create_ui(default_preset):
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['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['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['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)')
shared.gradio['skip_special_tokens'] = gr.Checkbox(value=shared.settings['skip_special_tokens'], label='Skip special tokens', info='Some specific models need this unset.')
shared.gradio['stream'] = gr.Checkbox(value=shared.settings['stream'], label='Activate text streaming')

1
settings-template.yaml
View File

@ -15,6 +15,7 @@ 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: ''