oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 06:35:15 +00:00
Code Issues Projects Releases Packages Wiki Activity

Dynamic Chat Message UI Update Speed (#6952)

Browse source
This commit is contained in:
mamei16 2025-05-05 23:05:23 +02:00 • committed by GitHub
parent 53d8e46502
commit 8137eb8ef4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 8 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

18
modules/text_generation.py
View file

@ -64,41 +64,39 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
all_stop_strings += st
shared.stop_everything = False
last_update = -1
reply = ''
is_stream = state['stream']
if len(all_stop_strings) > 0 and not state['stream']:
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
last_update = -1
latency_threshold = 1 / 1000
for reply in generate_func(question, original_question, state, stopping_strings, is_chat=is_chat):
cur_time = time.monotonic()
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
if state['max_tokens_second'] > 0:
diff = 1 / state['max_tokens_second'] - (cur_time - last_update)
if diff > 0:
time.sleep(diff)
last_update = time.time()
last_update = time.monotonic()
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
# If 'generate_func' takes less than 0.001 seconds to yield the next token
# (equivalent to more than 1000 tok/s), assume that the UI is lagging behind and skip yielding
if (cur_time - last_update) > latency_threshold:
yield reply
last_update = time.monotonic()
if stop_found or (state['max_tokens_second'] > 0 and shared.stop_everything):
break