Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
load_test.html | < 19 hours ago | 1.7 MB | |
load_test_stats.csv | < 19 hours ago | 564 Bytes | |
README.md | < 19 hours ago | 2.6 kB | |
v1.77.7.dev-gemma source code.tar.gz | < 19 hours ago | 198.7 MB | |
v1.77.7.dev-gemma source code.zip | < 19 hours ago | 201.2 MB | |
Totals: 5 Items | 401.6 MB | 0 |
What's Changed
- Fix litellm_param based costing by @Sameerlite in https://github.com/BerriAI/litellm/pull/15336
- Fix parallel tool calls in the Anthropic passthrough adapter by @lcfyi in https://github.com/BerriAI/litellm/pull/15315
- fix: redact AWS credentials when redact_user_api_key_info enabled by @timelfrink in https://github.com/BerriAI/litellm/pull/15321
- Add new Azure AI models with pricing details by @emerzon in https://github.com/BerriAI/litellm/pull/15387
- [Feat] Add EnkryptAI Guardrails on LiteLLM by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/15390
- [Fix] Fix dynamic Rate limiter v3 - inserting litellm_model_saturation by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/15394
- [Fix] - Sessions not being shared by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/15388
- fix: Prevents DB from accidentally overriding config file values if they are empty in DB by @ARajan1084 in https://github.com/BerriAI/litellm/pull/15340
- Temporarily relax ResponsesAPIResponse parsing to support custom backends (e.g., vLLM) by @ashengstd in https://github.com/BerriAI/litellm/pull/15362
- Fix - OpenRouter cache_control to only apply to last content block by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/15395
- [Fix]: remove panic from hot path by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/15396
New Contributors
- @lcfyi made their first contribution in https://github.com/BerriAI/litellm/pull/15315
- @ashengstd made their first contribution in https://github.com/BerriAI/litellm/pull/15362
Full Changelog: https://github.com/BerriAI/litellm/compare/v1.77.7.dev9...v1.77.7.dev-gemma
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.77.7.dev-gemma
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 ❌ | 120.0 | 153.84866007076198 | 6.427666207955637 | 6.427666207955637 | 1922 | 1922 | 92.73668699995596 | 5093.37253800004 |
Aggregated | Failed ❌ | 120.0 | 153.84866007076198 | 6.427666207955637 | 6.427666207955637 | 1922 | 1922 | 92.73668699995596 | 5093.37253800004 |