Skip to content

[Bugfix][V0] Multi-sequence logprobs streaming edge case #15259

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 22, 2025
Merged

[Bugfix][V0] Multi-sequence logprobs streaming edge case #15259

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0722da4
Handle multi-sequence logprobs edge case
andylolu2 Mar 21, 2025
763405f
Update outputs.py
andylolu2 Mar 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion vllm/outputs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,7 +223,12 @@ def from_seq_group(
if delta:
# Slice logprobs delta if applicable
if output_logprobs:
output_logprobs = output_logprobs[-num_output_tokens:]
# num_output_tokens can be 0 when n > 1 and request finishes
# before the others
if num_output_tokens > 0:
output_logprobs = output_logprobs[-num_output_tokens:]
else:
output_logprobs = None
# Don't include prompt if this is after the first output
# containing decode token ids
if include_prompt and seq.get_output_len() > num_output_tokens:
Expand Down