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.
Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.
| Vendor | Product | Versions | |
|---|---|---|---|
| ai inference server | 3.2 | — | |
| ai inference server | 3.4 | — | |
| enterprise linux ai | 3.4 | — | |
| Red Hat | Red Hat AI Inference Server | all versions | |
| Red Hat | Red Hat AI Inference Server 3.2 | all versions | |
| Red Hat | Red Hat AI Inference Server 3.4 | all versions | |
| Red Hat | Red Hat Enterprise Linux AI 3.4 | all versions | |
| Red Hat | Red Hat OpenShift AI (RHOAI) | all versions | |
| vllm-project | vllm | >= 0.1.0, < 0.19.0 |
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.1.0 < 0.19.0Our free, open-source honeypot sensor waits on ports your server does not use and reports the scanners and attackers that connect to a shared blocklist.