Skip to content
vLLMGHSA-wc36-9694-f9rf

vLLM Denial of Service via the best_of parameter

Medium6.2CVE-2024-8939 · Published Sep 17, 2024 · updated Aug 7, 2026

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.

GitHub advisory

Affected versions

PackageAffectedFixed in
vllm
PyPI
<= 0.5.0.post1No fix yet
Details and references
CVSS 3.1
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Severity from
GitHub (reviewed advisory)
Weakness
CWE-400
Also known as
CVE-2024-8939, PYSEC-2026-2025

More vLLM advisories

All vLLM
Advisory
vLLM Deserialization of Untrusted Data vulnerability
Critical9.8Mar 20, 2025
vLLM Allows Remote Code Execution via Mooncake Integration
Critical9.0Mar 19, 2025
vLLM denial of service via outlines unbounded cache on disk
Medium6.5Mar 19, 2025
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Low2.6Feb 6, 2025
vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
High7.5Jan 27, 2025
vLLM denial of service vulnerability
High7.5Sep 17, 2024

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.