Skip to content

fix(metrics): clarify chat-template fallback logging #509

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

Draft
YibaiMeng wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

fix(metrics): clarify chat-template fallback logging #509

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
6 changes: 3 additions & 3 deletions src/inference_endpoint/async_utils/services/metrics_aggregator/token_metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,9 +455,9 @@ def _warn_template_fallback(self, exc: Exception, impact: str) -> None:
if key in self._fallback_warned:
return
self._fallback_warned.add(key)
logger.exception(
"apply_chat_template failed for %s (%s); falling back to "
"whitespace tokenization. %s",
logger.info(
"apply_chat_template failed for %s (%s); "
"tokenizing as plain text instead. %s",
self._tokenizer_name,
type(exc).__name__,
impact,
Expand Down
Loading