github BerriAI/litellm v1.35.25

latest releases: v1.41.0, v1.40.31, v1.40.29...
2 months ago

What's Changed

  • [Fix] Add better observability for debugging lowest latency routing by @ishaan-jaff in #3283
  • [Feat] lowest-latency routing - penalize timeout errors from api endpoints by @ishaan-jaff in #3281

Full Changelog: 1.35.24.dev6...v1.35.25

Don't want to maintain your internal proxy? get in touch 🎉

Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

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 ✅ 95 104.03587220041199 1.616816849539448 0.0 484 0 88.34031499998218 1242.1794910000017
/health/liveliness Passed ✅ 79 83.35600463999175 15.319673702454356 0.0 4586 0 77.10968600002843 1444.1510330000256
/health/readiness Passed ✅ 79 82.3850293131141 15.309652110411756 0.0 4583 0 77.28314799999225 1293.70391599997
Aggregated Passed ✅ 79 83.93189565585871 32.24614266240556 0.0 9653 0 77.10968600002843 1444.1510330000256

Don't miss a new litellm release

NewReleases is sending notifications on new releases.