vLLM DeepSeek-OCR image processing vulnerable to denial of service

影響: pip:vllm >= 0.11.1, < 0.32.0 → 0.32.0

Any vLLM deployment serving a model of the DeepSeek-OCR family — deepseek-ai/DeepSeek-OCR, deepseek-ai/DeepSeek-OCR-2, or baidu/Unlimited-OCR (whose UnlimitedOCRForCausalLM subclasses DeepseekOCRForCausalLM) — can be killed by a single unauthenticated chat request carrying an ordinary, schema-valid PNG image, under completely default server configuration. The image model's input validation contains a guard inherited from the upstream DeepSeek-OCR reference implementation: python vllm/model_exec…

Read on GitHub Advisory Database

On 10/29/2026, 06:15 AM, GitHub Advisory Database published "vLLM DeepSeek-OCR image processing vulnerable to denial of service" (type: Advisory). Severity is "Medium" (medium). Related technologies: Python. CVE: CVE-2026-115914.