v1.55.10
版本发布时间: 2024-12-24 13:04:26
BerriAI/litellm最新发布版本:v1.56.9(2025-01-04 10:46:47)
What's Changed
- (Admin UI) - Test Key Tab - Allow typing in
model
name + Add wrapping for text response by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7347 - (Admin UI) - Test Key Tab - Allow using
UI Session
instead of manually creating a virtual key by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7348 - (refactor) - fix from enterprise.utils import ui_get_spend_by_tags by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7352
- (chore) - enforce model budgets on virtual keys as enterprise feature by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7353
- (Admin UI) correctly render provider name in /models with wildcard routing by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7349
- (Admin UI) - maintain history on chat UI by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7351
- Litellm enforce enterprise features by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7357
- Document team admins + Enforce assigning team admins as an enterprise feature by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7359
- Litellm docs update by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7365
- Complete 'requests' library removal by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7350
- (chore) remove unused code files by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7363
- (security fix) - update base image for all docker images to
python:3.13.1-slim
by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7388 - LiteLLM Minor Fixes & Improvements (12/23/2024) - p1 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7383
- LiteLLM Minor Fixes & Improvements (12/23/2024) - P2 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/7386
- [Bug Fix]: Errors in LiteLLM When Using Embeddings Model with Usage-Based Routing by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7390
- (Feat) Add input_cost_per_token_batches, output_cost_per_token_batches for OpenAI cost tracking Batches API by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7391
- (feat) Add basic logging support for
/batches
endpoints by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7381 - (feat) Add cost tracking for /batches requests OpenAI by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7384
- dd logger fix - handle objects that can't be JSON dumped by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/7393
Full Changelog: https://github.com/BerriAI/litellm/compare/v1.55.9...v1.55.10
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.55.10
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 ✅ | 200.0 | 218.24862748744047 | 6.256831142894005 | 0.0 | 1871 | 0 | 177.71721199983403 | 1940.1571020000574 |
Aggregated | Passed ✅ | 200.0 | 218.24862748744047 | 6.256831142894005 | 0.0 | 1871 | 0 | 177.71721199983403 | 1940.1571020000574 |
1、 load_test.html 1.59MB
2、 load_test_stats.csv 540B