scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-16 04:29:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 138
litellm/litellm-rust/crates/router
History
yujonglee 2aaa0b5d5c
refactor(rust-bridge): unify native call inputs and Messages settings (#45126) 
* refactor(rust): separate Messages settings from capability inputs

* refactor(rust-bridge): unify Messages OCR and Responses call inputs

* refactor(rust-bridge): share NativeCall across inference entrypoints

* fix(rust-bridge): preserve Responses URL aliases and public test inputs
2026-10-07 15:05:43 -07:00
..
src refactor(rust): extract inference-messages crate (#44818) 2026-10-06 07:17:26 -07:00
tests refactor(rust-bridge): unify native call inputs and Messages settings (#45126) 2026-10-07 15:05:43 -07:00
Cargo.toml refactor(rust): extract inference-messages crate (#44818) 2026-10-06 07:17:26 -07:00
README.md chore(rust): prune inference deps and rewrite layering docs (#44836) 2026-10-06 07:17:27 -07:00

README.md

litellm-router scaffolds the model-list setup and deployment lookup portion of Python's litellm.Router. Router::from_model_list(&config.model_list) maps configured public names to provider deployments. Programmatic callers can collect (String, Deployment) entries into a Router

Lookup is exact and returns None for an unknown name. This extraction preserves the gateway's existing behavior: the last entry wins when public names repeat. Multiple deployments per model group, routing strategies, retries, cooldowns, and fallbacks are not implemented yet

The router owns deployment configuration and selection. The gateway handles HTTP errors and responses, while the inference-<fmt> crates execute provider calls and resolve credentials