LLMMedium
CVE-2025-48956: vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.…
- Occurred
- Aug 21, 2025
- Published
- Aug 21, 2025
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2025-48956
- cvss:HIGH
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: vLLM is an LLM serving engine with a DoS vulnerability, but no confirmed mass casualty or major financial loss reported.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8