NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service.Referenceshttps://nvd.nist.gov/vuln/detail/CVE-2026-24271https://www.cve.org/CVERecord?id=CVE-2026-24271
