What's Changed
- (perf improvement proxy) use one async async_batch_set_cache in parallel request limiter by @ishaan-jaff in #5956
- (fix proxy) model_group/info support rerank models by @ishaan-jaff in #5955
- (perf improvement proxy) use one redis set cache to update spend in db (30-40% perf improvement) by @ishaan-jaff in #5960
- (perf proxy) don't run redis async_set_cache_pipeline when empty list passed to it by @ishaan-jaff in #5962
- [Feat Proxy] Allow using hypercorn for http v2 by @ishaan-jaff in #5950
- (feat proxy prometheus) track virtual key, key alias, error code, error code class on prometheus by @ishaan-jaff in #5968
- (proxy prometheus) track api key and team in latency metrics by @ishaan-jaff in #5966
- (feat prometheus proxy) track remaining team and key alias in deployment failure metrics by @ishaan-jaff in #5967
- (proxy docker) add sentry sdk to litellm docker by @ishaan-jaff in #5965
Full Changelog: v1.48.5...v1.48.6
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.48.6
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 ✅ | 110.0 | 123.41082122468366 | 6.334644427987359 | 0.0 | 1896 | 0 | 88.9820840000084 | 3007.4007179999853 |
| Aggregated | Passed ✅ | 110.0 | 123.41082122468366 | 6.334644427987359 | 0.0 | 1896 | 0 | 88.9820840000084 | 3007.4007179999853 |