scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49
26461 commits 3118 branches 1436 tags 4.4 GiB
Commit graph

26461 commits

This branch
This branch
All branches
Author SHA1 Message Date
AlexsanderHamir
56838e2388 test: ensure model_names is a O(1) datastructure 2025-10-15 17:52:44 -07:00
AlexsanderHamir
6e4da1da65 perf(router): optimize model lookups with O(1) data structures 
Replace O(n) scans with index map lookups and convert model_names to set. Standardize timing calls.
 2025-10-15 16:43:08 -07:00
Ishaan Jaff
65163c7ccb [Fix] GEMINI - CLI - add google_routes to llm_api_routes (#15500) 
* fix: add google_routes to llm_api_routes

* test: test_virtual_key_llm_api_routes_allows_google_routes
 2025-10-14 13:57:39 -07:00
Krrish Dholakia
b0d963cc0c docs(index.md): bump rc 2025-10-14 13:57:39 -07:00
Krrish Dholakia
cb29e33cad docs: fix doc 2025-10-14 13:57:39 -07:00
Dhruv Yadav
b57406e53e add tests for openrouter cost tracking 2025-10-14 13:57:39 -07:00
Dhruv Yadav
09662b5081 direct cost calculation from openrouter 2025-10-14 13:57:39 -07:00
AlexsanderHamir
2e57d19a55 update benchmarks 2025-10-14 13:57:39 -07:00
AlexsanderHamir
6df051e87b docs: update benchmark results with improved infrastructure 
- Update to 2 instance baseline (1035 RPS @ 200ms median)
- Add 4 instance results (1170 RPS @ 100ms median)
- Update machine specs to 4 CPU / 8GB RAM
- Update Locust settings to 1000 users
 2025-10-14 13:57:39 -07:00
kowyo
92bd238b87 fix comment 2025-10-14 13:57:39 -07:00
kowyo
6896c60b5b fix: only use think level for gpt-oss model 2025-10-14 13:57:39 -07:00
Kowyo
9557a37d37 fix: update 'think' parameter assignment to use provided value in transformation.py 2025-10-14 13:57:39 -07:00
Kowyo
e30b716ba8 fix: add 'think' parameter handling in ollama_chat.py 2025-10-14 13:57:39 -07:00
Kowyo
4f33bc4e46 fix(ollama/chat): 'think' param handling 2025-10-14 13:57:39 -07:00
mubashir1osmani
6424480571 add ecs to docs 2025-10-14 13:57:39 -07:00
huangyafei
9a980f36d4 Add anthropic/claude-sonnet-4.5 to OpenRouter cost map 2025-10-14 13:57:39 -07:00
Krish Dholakia
ff20f8402a
Merge pull request #15456 from BerriAI/litellm_staging_branch_10_11_2025_p1 
Litellm staging branch 10 11 2025 p1
 2025-10-12 22:01:45 -07:00
Krrish Dholakia
0ffc81f010 fix: fix reformatting 2025-10-12 22:01:16 -07:00
Krrish Dholakia
1949436047 test: update test 2025-10-12 21:58:06 -07:00
Krish Dholakia
04dc9d091c
Merge branch 'main' into litellm_staging_branch_10_11_2025_p1 2025-10-12 21:55:44 -07:00
Ishaan Jaffer
e761665f22 docs fix 2025-10-11 18:21:35 -07:00
Imad Saddik
133189e191
Fixed a few typos (#15267) 2025-10-11 17:53:42 -07:00
Hampus Näsström
e650f39821
Reduce claude-4-sonnet max_output_tokens to 64k (#15409) 
Claude 4 Sonnet doesn't support more than 64k output tokens: https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4
 2025-10-11 17:51:27 -07:00
Copilot
f5359ba007
Fix apply_guardrail endpoint returning raw string instead of ApplyGuardrailResponse (#15436) 
* Initial plan

* Fix apply_guardrail endpoint to return ApplyGuardrailResponse

Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com>
 2025-10-11 17:50:37 -07:00
Alexsander Hamir
300a142926
[Add]: perf summary (#15458) 
* add: perf summary

* update docs

* fix: focus on p99
 2025-10-11 17:38:13 -07:00
Krrish Dholakia
78e2274381 fix(pass_through_endpoints.py): use path instead of endpoint 
includes the mapped route
 2025-10-11 17:04:56 -07:00
jlan-nl
328505dcda
Fix prices (#15374) 
Co-authored-by: IQHL (Hans Jacob Landelius) <iqhl@novnordisk.com>
 2025-10-11 16:53:55 -07:00
Ishaan Jaffer
087bd2d306 docs fix 2025-10-11 16:49:11 -07:00
Krrish Dholakia
3ee3cb945d fix(team_endpoints.py): document new param 2025-10-11 16:45:55 -07:00
Krrish Dholakia
a71329fbe1 fix: fix linting errors 2025-10-11 16:42:22 -07:00
Krrish Dholakia
2266b272aa fix(proxy/_types.py): fix default to be none 2025-10-11 16:41:03 -07:00
Krrish Dholakia
23870cbda0 fix(pass_through_endpoints.py): fix typo 2025-10-11 16:38:32 -07:00
Ishaan Jaffer
1ccd949495 docs fix 2025-10-11 16:34:47 -07:00
Ishaan Jaffer
b9fef02f04 docs v1.78.0 2025-10-11 16:33:46 -07:00
Ishaan Jaffer
7288f4355f docs fix 2025-10-11 16:24:21 -07:00
Ishaan Jaffer
54b8bde60c docs fix 2025-10-11 16:23:46 -07:00
Krrish Dholakia
a7456ab21e refactor: refactor to cut down large functions 2025-10-11 16:18:37 -07:00
Ishaan Jaffer
8d29fc8cdd docs 2025-10-11 16:12:00 -07:00
Krrish Dholakia
6bd722bba4 fix: always retain config models 2025-10-11 16:09:33 -07:00
Krrish Dholakia
8eb58db989 fix: fix linting error 2025-10-11 15:42:53 -07:00
Krrish Dholakia
090a2c0cfe fix: remove unused uuid import 2025-10-11 15:38:28 -07:00
Krrish Dholakia
f96f2106f7 fix(pass_through_endpoints.py): fix check for mapped routes 2025-10-11 15:32:48 -07:00
Krish Dholakia
8c4c4acda2
Merge pull request #15457 from BerriAI/litellm_docs_10_11_2025 
Litellm docs 10 11 2025
 2025-10-11 15:16:13 -07:00
Krrish Dholakia
3f921d8dbe docs(index.md): document mcp oauth support 2025-10-11 15:14:15 -07:00
Krrish Dholakia
9b5943ae50 docs: cleanup docs 2025-10-11 15:09:24 -07:00
Krrish Dholakia
fdaa163758 docs(claude_responses_api.md): update docs with mcp server tutorial 2025-10-11 15:07:54 -07:00
Ishaan Jaffer
e4f3d78579 docs v1.78.0.rc.1 2025-10-11 14:57:28 -07:00
Krrish Dholakia
73257be604 docs(index.md): initial commit for github mcp oauth docs 2025-10-11 14:00:50 -07:00
Krish Dholakia
323389c244
(feat) Passthrough - allow admin to give access to specific passthrough endpoints 
(feat) Passthrough - allow admin to give access to specific passthrough endpoints
 2025-10-11 13:51:10 -07:00
Krrish Dholakia
4360e19322 fix: fix indent 2025-10-11 13:50:37 -07:00