VLLM_FALLBACK=0 to disable the opt-in fallback behavior.Models & inference
vLLM fallback
Use a local vLLM OpenAI-compatible server as an Arka fallback provider.
Start vLLM, then enable it in Arka’s fallback chain:
Arka tries vLLM when it is reachable or explicitly configured, then continues
through the normal provider chain if the local server fails. Set