oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-20 22:13:43 +00:00
Code Issues Projects Releases Packages Wiki Activity

Revert gradio to 3.50.2 (#5513)

Browse source
This commit is contained in:
oobabooga 2024-02-15 20:40:23 -03:00 • committed by GitHub
parent ea0e1feee7
commit 080f7132c0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 61 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

14
modules/text_generation.py
View file

@ -80,16 +80,19 @@ 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()
# Limit number of tokens/second to make text readable in real time
# Maximum number of tokens/second
if state['max_tokens_second'] > 0:
diff = 1 / state['max_tokens_second'] - (cur_time - last_update)
if diff > 0:
@ -97,8 +100,13 @@ 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:
yield reply
if cur_time - last_update > min_update_interval:
last_update = cur_time
yield reply
if stop_found or (state['max_tokens_second'] > 0 and shared.stop_everything):
break