Allocation of Resources Without Limits or Throttling Affecting tritonserver-backend-vllm-cuda-13.0 package, versions <25.11-r7

Note: Versions mentioned in the description apply only to the upstream tritonserver-backend-vllm-cuda-13.0 package and not the tritonserver-backend-vllm-cuda-13.0 package as distributed by Chainguard. See How to fix? for Chainguard relevant fixed versions and status.

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.

• https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380
• https://github.com/vllm-project/vllm/pull/37952
• https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528