CVE-2025-48956: Vllm

High severity, CVSS 7.5. EPSS: 0.6% chance of exploitation in the next 30 days.

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.

Affected products

• Vllm Vllm: from 0.1.0, before 0.10.1.1 (fixed in 0.10.1.1)

Published 2025-08-21. Last modified 2026-06-17.