Skip to content

[generation] Fix misleading synced_gpus warning in continuous batching #47158

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

Open
Partha-Shankar wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[generation] Fix misleading synced_gpus warning in continuous batching #47158

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1c18627
[generation] Fix misleading synced_gpus warning in continuous batching
Partha-Shankar Jul 8, 2026
63e2072
Remove regression test per maintainer review feedback
Partha-Shankar Jul 13, 2026
eaf8388
Merge branch 'main' into generation-fix-synced-gpus-warning
remi-or Jul 13, 2026
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
2 changes: 1 addition & 1 deletion src/transformers/generation/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2418,7 +2418,7 @@ def generate(

# others are ignored
if synced_gpus is not None:
logger.warning(f"synced_gpus is not ignored for continuous batching. Got {synced_gpus = }")
logger.warning(f"synced_gpus is ignored for continuous batching. Got {synced_gpus = }")
num_beams = kwargs.get("num_beams", 1)
if num_beams > 1: # FIXME: remove this once CB supports num_beams (which is planned)
logger.warning(f"num_beams is not supported for continuous batching yet. Got {num_beams = }. ")
Expand Down
Loading