6 views
-/https://github.com/berriai/litellm/issues/25688
GitHub · issue

#25688 [Feature]: OCI provider: Cannot set servingType to DEDICATED (UI missing option)

  • State: open
  • Author: @kareemalkoul
  • Labels: enhancement, ui-dashboard

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

When configuring the OCI provider in LiteLLM, the parameter servingType is automatically set to ON_DEMAND by default. However, there is no option in the UI to change this value to DEDICATED.

### Motivation, pitch

I'm working on integrating OCI as a provider in LiteLLM, specifically targeting deployments that require DEDICATED serving type.

Currently, the servingType parameter is automatically set to ON_DEMAND, and there is no way to override this value through the UI. This creates a limitation when working with OCI setups that require DEDICATED, making it impossible to fully configure the provider from the UI.

This feature request is motivated by the need to support a broader range of OCI deployment configurations directly within LiteLLM, without requiring manual workarounds or code-level changes.

Providing an option to select servingType (e.g., ON_DEMAND vs DEDICATED) would improve flexibility and make OCI integration more complete and production-ready.

### What part of LiteLLM is this about?

UI Dashboard

### LiteLLM is hiring a founding …

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (2 events)
#0 of 0 · 31d18h44m3s ago — entered · #import:https:::github.com:berriai:litellm post #2236
32614 is harder because it requires correcting asynchronous coordination and cache-consistency behavior across shared proxy budget paths, with concurrency-sensitive regression testing; 25688 is comparatively localized to exposing and wiring a provider configuration choice in the dashboard.
#0 of 0 · 31d18h23m55s ago — current · #import:https:::github.com:berriai:litellm post #2551
The right task is harder because it likely spans dashboard controls, configuration plumbing, validation, and compatibility testing across OCI deployment modes, while the left appears confined to a localized normalization and billing correction with focused regression coverage.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search