oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-04 15:50:26 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Make the llama.cpp prompt processing messages shorter

Browse source
This commit is contained in:
oobabooga 2025-06-10 14:03:25 -07:00
parent 889153952f
commit 18bd78f1f0
1 changed files with 9 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
modules/llama_cpp_server.py
View file

@ -422,9 +422,17 @@ def filter_stderr_with_progress(process_stderr):
if match:
progress = float(match.group(1))
# Extract just the part from "prompt processing" onwards
prompt_processing_idx = line.find('prompt processing')
if prompt_processing_idx != -1:
display_line = line[prompt_processing_idx:]
else:
display_line = line # fallback to full line
# choose carriage return for in-progress or newline at completion
end_char = '\r' if progress < 1.0 else '\n'
print(line, end=end_char, file=sys.stderr, flush=True)
print(display_line, end=end_char, file=sys.stderr, flush=True)
last_was_progress = (progress < 1.0)
# skip noise lines