vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

不加限制或调节的资源分配

vLLM 安全漏洞

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.1.0至0.19.0之前版本存在安全漏洞，该漏洞源于ChatCompletionRequest和CompletionRequest Pydantic模型中n参数缺少上限验证，可能导致未经验证的攻击者通过发送单个HTTP请求造成拒绝服务攻击。

N/A

N/A