Fedora Account System
Red Hat Associate
Red Hat Customer
An improper timeout handling vulnerability exists in the ilab model serve component, which wraps the vllm JSON web API for interaction with a Large Language Model (LLM). When processing completion requests, the API accepts a parameter best_of that can cause excessive processing time if set to a large value. This improper handling can lead to a Denial of Service (DoS), making the API unresponsive to legitimate users. The issue primarily affects instances where the API is exposed beyond localhost.