What's Changed
- (feat) Arize - Allow using Arize HTTP endpoint by @ishaan-jaff in #6364
- LiteLLM Minor Fixes & Improvements (10/22/2024) by @krrishdholakia in #6384
- build(deps): bump http-proxy-middleware from 2.0.6 to 2.0.7 in /docs/my-website by @dependabot in #6395
- (docs + testing) Correctly document the timeout value used by litellm proxy is 6000 seconds + add to best practices for prod by @ishaan-jaff in #6339
- (refactor) move convert dict to model response to llm_response_utils/ by @ishaan-jaff in #6393
- (refactor) litellm.Router client initialization utils by @ishaan-jaff in #6394
- (fix) Langfuse key based logging by @ishaan-jaff in #6372
- Revert "(refactor) litellm.Router client initialization utils " by @ishaan-jaff in #6403
- (fix) using /completions with
echoby @ishaan-jaff in #6401 - (refactor) prometheus async_log_success_event to be under 100 LOC by @ishaan-jaff in #6416
- (refactor) router - use static methods for client init utils by @ishaan-jaff in #6420
- (code cleanup) remove unused and undocumented logging integrations - litedebugger, berrispend by @ishaan-jaff in #6406
Full Changelog: v1.50.2...v1.50.4
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.50.4
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 | Failed ❌ | 280.0 | 312.6482922531862 | 6.037218908394318 | 0.0 | 1805 | 0 | 231.8999450000092 | 2847.2051709999846 |
| Aggregated | Failed ❌ | 280.0 | 312.6482922531862 | 6.037218908394318 | 0.0 | 1805 | 0 | 231.8999450000092 | 2847.2051709999846 |