litellm

mirror of https://github.com/tiennm99/litellm.git synced 2026-06-18 09:32:08 +00:00

Files

T

Krish Dholakia 9cc39af131 Add vertex ai meta llama 4 support + handle tool call result in content for vertex ai (#10492 )

* refactor(vertex_ai/llama): handle response transformation within config

Allows us to handle https://github.com/BerriAI/litellm/issues/10441#issuecomment-2844975599

* fix(vertex_ai/llama): handle tool call in content

Fixes https://github.com/BerriAI/litellm/issues/10441

* fix(vertex_ai/llama): return 'tool_calls' as finish reason if tool call returned

vertex ai returns stop

* feat(vertex_ai/): cost tracking for vertex_ai/meta/llama-4

* ci(test-linting.yml): pin openai version

* build: reorder pinning

* ci(pyproject.toml): limit openai version

temporary patch as new version has linting errors

* ci(pyproject.toml): limit openai version

temporary patch around linting errors

* ci(limit-openai-version): temporary patch

* fix: fix linting errors

* fix: fix linting error

* fix(parallel_request_limiter_v2.py): add team based multi-instance rate limiting

* fix: fix linting errors

* build(pyproject.toml): modify pin

* ci: bump pin

2025-05-01 22:47:06 -07:00

auto_update_price_and_context_window_file.py

Added the requested features of Merlinvt ("1.If the model is not multimodal, there is no info needed for input_cost_per_image. Right now it's 0.0 for a lot of models.

2024-05-22 16:10:39 +09:30

auto_update_price_and_context_window.yml

bring back model_prices_and_context_window update yml job

2024-08-20 12:09:54 -07:00

ghcr_deploy.yml

fixes for EE image

2025-04-26 15:43:21 -07:00

ghcr_helm_deploy.yml

allow configuring httpx hooks for AsyncHTTPHandler (#6290 ) (#6415 )