Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.
Problem types
CWE-400: Uncontrolled Resource Consumption
Product status
References
github.com/...t/vllm/security/advisories/GHSA-rxc4-3w6r-4v47
github.com/vllm-project/vllm/pull/23267
github.com/...ommit/d8b736f913a59117803d6701521d2e4861701944
