Description
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.
Problem types
CWE-770: Allocation of Resources Without Limits or Throttling
Product status
References
github.com/...t/vllm/security/advisories/GHSA-3mwp-wvh9-7528
github.com/vllm-project/vllm/pull/37952
github.com/...ommit/b111f8a61f100fdca08706f41f29ef3548de7380