mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
Replace racy check-then-increment RPM logic with atomic increment-first pattern to prevent concurrent requests from bypassing the rate limit. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| test_enforce_model_rate_limits.py | ||