CVE-2026-24271

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.

Score
CVSS 3.1 6.2 Medium
Status
Deferred - psirt@nvidia.com
Published
2026-07-14
Last modified
2026-10-24
Weaknesses
CWE-770

Affected products

References