scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

chore(router): remove in-repo escalation docs
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Details
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
Details

Browse source
This commit is contained in:
Tin 2026-09-19 10:26:42 -07:00
parent e9109ddf4a
commit 5f722bc195
1 changed files with 0 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
litellm/router_strategy/complexity_router/README.md
View file

@ -68,19 +68,6 @@ still resolve to a deployment in `model_list`; this configuration does not creat
- abc
```
### Context-window escalation
Context-window escalation is opt-in. Omit `enable_context_window_escalation` or set it to
`false` to keep the complexity-selected model without context-window replacement or filtering
Set `enable_context_window_escalation: true` inside `complexity_router_config` to restrict the
selected tier to models whose declared windows fit the prompt, or move to the lowest configured
tier with a fitting model when none in the selected tier fit. Unknown windows do not justify
moving a request. `context_window_escalation_buffer` defaults to `0.95`
Existing saved configurations with explicit `true` keep escalation enabled. Configurations that
omit the setting now default to disabled; set it to `true` to retain their previous behavior
### Capability forecasting
Set `classifier_type: capability` to use