CVE-2026-24271 | NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-c… | CVSS 6.2 MEDIUM

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.

Metadata

CVE ID: CVE-2026-24271
State: PUBLISHED
Assigner: nvidia
Reserved: 2026-01-21 19:09 UTC
Published: 2026-07-14 20:09 UTC
Last updated: 2026-07-14 20:09 UTC
Primary CWE: CWE-770
CWE-770 Allocation of Resources Without Limits or Throttling
Vendor / Product: NVIDIA / TensorRT-LLM
Sources: cve.org · NVD

Severity & Metrics

6.2 MEDIUM CVSS 3.1

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

Affected products (1)

Vendor	Product	Platform	Versions
NVIDIA	TensorRT-LLM	—	0.0 ≤ v1.3.0 rc14

Weakness (CWE)

CWE	Source	Description
CWE-770	cna	CWE-770 Allocation of Resources Without Limits or Throttling

CVSS scores (1)

Score	Severity	Version	Source	Vector
6.2	MEDIUM	3.1	cna	CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References (2)