CVE-2026-24271

MEDIUM

Nvidia TensorRT-LLM < v1.3.0 rc14 - Allocation of Resources Without Limits or Throttling

Title source: rule

Description

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.

References (2)

Core 2

Core References

https://nvd.nist.gov/vuln/detail/CVE-2026-24271

https://www.cve.org/CVERecord?id=CVE-2026-24271

Scores

CVSS v3 6.2

EPSS 0.0012

EPSS Percentile 2.2%

Attack Vector LOCAL

CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CISA SSVC

Vulnrichment

Exploitation none

Automatable no

Technical Impact partial

Details

CWE

CWE-770

Status published

Products (1)

NVIDIA/TensorRT-LLM 0.0 - v1.3.0 rc14

Published Jul 14, 2026

Tracked Since Jul 15, 2026