What's Changed
- fix(handle_jwt.py): enable team-based jwt-auth access by @krrishdholakia in #2704
- (fix) Remove print statements from append_query_params by @antoniomdk in #2697
- Fix Ollama embedding by @onukura in #2675
- enable new
/team/disable
endpoint by @krrishdholakia in #2705 - feat(llm_guard.py): enable key-specific llm guard check by @krrishdholakia in #2706
New Contributors
- @antoniomdk made their first contribution in #2697
- @onukura made their first contribution in #2675
Full Changelog: v1.34.4.dev2...v1.34.5
Load Test LiteLLM Proxy Results
Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
---|---|---|---|---|---|---|---|---|---|
/chat/completions | Passed ✅ | 80 | 91.09598086965796 | 1.5630632104195936 | 0.0 | 468 | 0 | 75.90920399997003 | 1370.1692500000036 |
/health/liveliness | Passed ✅ | 66 | 68.46346034574393 | 15.340062661233318 | 0.0 | 4593 | 0 | 63.58234399999674 | 1380.5088000000012 |
/health/readiness | Passed ✅ | 66 | 69.07605037803246 | 15.416879870292401 | 0.0 | 4616 | 0 | 63.49641600002087 | 1383.9997339999854 |
Aggregated | Passed ✅ | 66 | 69.8502264090107 | 32.320005741945316 | 0.0 | 9677 | 0 | 63.49641600002087 | 1383.9997339999854 |