Skip to content

[Perf] Skip detokenization in online beam search #1

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

Closed
GuyStone wants to merge 1 commit into from
Closed

[Perf] Skip detokenization in online beam search #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions vllm/entrypoints/generate/beam_search/online.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,11 @@ async def beam_search(
logprobs=logprobs_num,
max_tokens=1,
temperature=temperature,
# Beam search ranks candidates by logprob and detokenizes the final
# sequences itself (see ``tokenizer.decode`` below), so the engine's
# per-step detokenization of all ``2 * beam_width`` logprob token ids
# is pure overhead -- O(beam_width) wasted decodes every step. Skip it.
detokenize=False,
)
all_beams = [
BeamSearchSequence(
Expand Down
Loading