Description
A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
vllm
Default version status: unaffected
0 to < 0.5.0.post1affected
Red Hat Red Hat Enterprise Linux AI (RHEL AI)
Default version status: affected
Red Hat Red Hat Enterprise Linux AI (RHEL AI)
Default version status: affected