Commit graph

15126 commits

Author SHA1 Message Date
Sophia Loris
d5c65c6be2 Add support for Triton streaming & triton async completions 2024-07-19 09:35:27 -05:00
Krish Dholakia
2ad1c0455a
Merge pull request #4773 from titusz/patch-1
Add missing `num_gpu` ollama configuration parameter
2024-07-18 22:47:39 -07:00
Krish Dholakia
5e7172d0e7
Merge pull request #4783 from areibman/remove_bad_model
Removed weird replicate model from model prices list
2024-07-18 22:47:21 -07:00
Krrish Dholakia
c56456be64 fix(anthropic.py): revert client to requests library 2024-07-18 22:45:41 -07:00
Ishaan Jaff
086486c5c3 bump: version 1.41.24 → 1.41.25 2024-07-18 22:40:51 -07:00
Marc Abramowitz
780a6293dc Alias /health/liveliness as /health/liveness
The latter is the more common term in Kubernetes, so it's nice to support that.
2024-07-18 22:40:51 -07:00
Ishaan Jaff
6f393be66b docs - tag based routing 2024-07-18 22:40:51 -07:00
Ishaan Jaff
d9c051adff add tags to metadata 2024-07-18 22:40:51 -07:00
Ishaan Jaff
fa26d3f96f fix test 2024-07-18 22:40:51 -07:00
Ishaan Jaff
56489ad9cc rename doc 2024-07-18 22:40:51 -07:00
Ishaan Jaff
1ab5c1a227 check if using tag based routing 2024-07-18 22:40:51 -07:00
Ishaan Jaff
52d0f6a808 control using enable_tag_filtering 2024-07-18 22:40:51 -07:00
Ishaan Jaff
e298515034 fix use tags as a litellm param 2024-07-18 22:40:51 -07:00
Ishaan Jaff
79c5788ad9 fix remove previous code on free/paid tier 2024-07-18 22:40:51 -07:00
Ishaan Jaff
ad46e6a61f router - refactor to tag based routing 2024-07-18 22:40:51 -07:00
Ishaan Jaff
38c50e674e fix ui make ui session last 24 hours 2024-07-18 22:40:51 -07:00
Krrish Dholakia
db3063d3d3 test: fix test 2024-07-18 22:40:51 -07:00
Ishaan Jaff
d42963a0ae router - use free paid tier routing 2024-07-18 22:40:51 -07:00
Ishaan Jaff
b0f0898f2f helper to get_deployments_for_tier 2024-07-18 22:40:51 -07:00
Krrish Dholakia
af0d30e41e docs(json_mode.md): add json mode to docs 2024-07-18 22:40:35 -07:00
Krrish Dholakia
f2401d6d5e feat(vertex_ai_anthropic.py): support response_schema for vertex ai anthropic calls
allows passing response_schema for anthropic calls. supports schema validation.
2024-07-18 22:40:35 -07:00
Ishaan Jaff
4bde501ee1 bump: version 1.41.24 → 1.41.25 2024-07-18 22:20:39 -07:00
Ishaan Jaff
154fa64d0a
Merge pull request #4781 from msabramo/liveness-alias-of-liveliness
Alias  `/health/liveliness` as `/health/liveness`
2024-07-18 22:20:09 -07:00
Ishaan Jaff
f04397e19a
Merge pull request #4789 from BerriAI/litellm_router_refactor
[Feat-Router] - Tag based routing
2024-07-18 22:19:18 -07:00
Ishaan Jaff
4dff995932
Merge pull request #4787 from BerriAI/litellm_increase_default_session_time_ui
[Fix] Admin UI - make ui session last 12 hours
2024-07-18 22:19:09 -07:00
Ishaan Jaff
a4338bec11 docs - tag based routing 2024-07-18 22:18:10 -07:00
Krrish Dholakia
a0ac3e3c7d test: fix test 2024-07-18 22:05:47 -07:00
Ishaan Jaff
502b739b33 add tags to metadata 2024-07-18 21:55:53 -07:00
Ishaan Jaff
331e2bbc17 fix test 2024-07-18 21:49:36 -07:00
Ishaan Jaff
ab17aa3919 rename doc 2024-07-18 21:48:24 -07:00
Krish Dholakia
17575b1846
Merge pull request #4784 from BerriAI/litellm_anthropic_response_schema_support
feat(vertex_ai_anthropic.py): support response_schema for vertex ai anthropic calls
2024-07-18 20:40:22 -07:00
Krish Dholakia
967964a51c
Merge branch 'main' into litellm_anthropic_response_schema_support 2024-07-18 20:40:16 -07:00
Ishaan Jaff
f8bdfe7cc3 fix test amazing vertex medlm 2024-07-18 20:35:14 -07:00
Ishaan Jaff
946db012d4 docs free/paid tier 2024-07-18 20:35:14 -07:00
Ishaan Jaff
9f02fb5a33 docs using free, paid tier 2024-07-18 20:35:14 -07:00
Ishaan Jaff
59d599d5fd test adding free / paid tier to metadata 2024-07-18 20:35:14 -07:00
Ishaan Jaff
de8c92b11d feat - enterprise 2024-07-18 20:35:14 -07:00
Ishaan Jaff
0e70b5df14 router - use free paid tier routing 2024-07-18 20:35:14 -07:00
Ishaan Jaff
229b7a6493 helper to get_deployments_for_tier 2024-07-18 20:35:14 -07:00
Ishaan Jaff
dfc674622b litellm router - use free / paid tier 2024-07-18 20:35:14 -07:00
Ishaan Jaff
f3e0a89597 check if using tag based routing 2024-07-18 20:10:45 -07:00
Ishaan Jaff
08adda7091 control using enable_tag_filtering 2024-07-18 19:39:04 -07:00
Krrish Dholakia
96471c145e fix(bedrock_httpx.py): support jamba streaming 2024-07-18 19:36:50 -07:00
Ishaan Jaff
071091fd8c fix use tags as a litellm param 2024-07-18 19:34:45 -07:00
Ishaan Jaff
b6e60d481e fix remove previous code on free/paid tier 2024-07-18 19:24:13 -07:00
Ishaan Jaff
4d0fbfea83 router - refactor to tag based routing 2024-07-18 19:22:09 -07:00
Krrish Dholakia
cece76c4ee feat(bedrock_httpx.py): add ai21 jamba instruct as converse model
initial commit for adding ai21 jamba instruct support through bedrock converse
2024-07-18 18:24:06 -07:00
Ishaan Jaff
51525254e8 fix ui make ui session last 24 hours 2024-07-18 18:22:40 -07:00
Ishaan Jaff
81c77f33b8 fix test amazing vertex medlm 2024-07-18 18:16:00 -07:00
Ishaan Jaff
4b96cd46b2
Merge pull request #4786 from BerriAI/litellm_use_model_tier_keys
[Feat-Enterprise] Use free/paid tiers for Virtual Keys
2024-07-18 18:07:09 -07:00