scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36
34106 commits 4135 branches 1402 tags 2.1 GiB
Commit graph

4 commits

Author SHA1 Message Date
Julio Quinteros Pro
61d35cac34 fix: use atomic increment-first pattern for model RPM rate limiting 
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>
 2026-02-24 09:55:07 -03:00
Julio Quinteros Pro
737a04b3ea Revert "Merge pull request #21957 from jquinter/fix/flaky-rpm-limit-test" 
This reverts commit 77453ada2a, reversing
changes made to 7622f26918.
 2026-02-24 09:52:50 -03:00
Julio Quinteros Pro
75d9f4d84f fix: use atomic increment-first pattern for model RPM rate limiting 
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>
 2026-02-23 19:11:52 -03:00
Harshit Jain
6d86808eaf feat: enforce model-level TPM/RPM limits (enforce_model_rate_limits) … (#19230) 
* feat: enforce model-level TPM/RPM limits (enforce_model_rate_limits) flag

* fix lint errors
 2026-02-02 18:18:46 +05:30