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 su…

Published: 2026-07-14 · CVSS: 6.2 · CVSS 3.1

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.

Original CVE JSON · STIX 2.1

Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7