CVE-2026-24271

Published Jul 14, 2026 CVSS 3.1 · 6.2 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

NVIDIA TensorRT‑LLM has a flaw in its OpenAI‑compatible inference API that permits an attacker to trigger unlimited GPU memory allocation. The vulnerability is a classic resource exhaustion weakness, which can consume all available GPU resources and render the inference service inoperable. Consequently, a successful exploit could lead to a denial‑of‑service scenario affecting any client relying on the TensorRT‑LLM endpoint for predictions.

Affected Systems

The affected product is NVIDIA TensorRT‑LLM. No specific version range is provided in the data, so all releases of TensorRT‑LLM that implement the OpenAI‑compatible inference API may be impacted.

Risk and Exploitability

The CVSS score of 6.2 indicates a moderate severity, and the EPSS score of less than 1% suggests exploitation is currently unlikely to be observed in the wild. The vulnerability is not listed in CISA's KEV catalog. Based on the description, the attack vector is inferred to be remote via the public inference API. An adversary would need to make repeated inference requests that trigger excessive GPU memory allocation, but no additional authentication or privilege escalation is required.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Check NVIDIA's official website or product release notes for a TensorRT‑LLM patch that mitigates the resource exhaustion issue.
  • If a patch is not yet available, configure the inference API to enforce explicit GPU allocation limits or per‑user quotas to prevent unbounded GPU usage.
  • Monitor GPU resource consumption and set alerts for abnormal spikes that could indicate exploitation attempts.

Generated by OpenCVE AI on August 1, 2026 at 09:15 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
Title Unlimited GPU Memory Allocation Causing Denial of Service in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
Title Unlimited GPU Memory Allocation Causing Denial of Service in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
Title Unbounded GPU Resource Allocation Causing Resource Exhaustion in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
Title Unbounded GPU Resource Allocation Causing Resource Exhaustion in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
Title Unlimited GPU Memory Allocation via OpenAI API in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
Title Unlimited GPU Memory Allocation via OpenAI API in NVIDIA TensorRT‑LLM
Type Values Removed Values Added
First Time appeared Nvidia
Nvidia tensorrt-llm
Vendors & Products Nvidia
Nvidia tensorrt-llm
Type Values Removed Values Added
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.
Weaknesses CWE-770
References
Metrics cvssV3_1

{'score': 6.2, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}

Weaknesses
  • CWE-770

    Allocation of Resources Without Limits or Throttling

Sources

Status
PUBLISHED
Assigner
nvidia
Published
Updated
Jul 15, 2026, 2:18 PM
Reserved
Jan 21, 2026, 7:09 PM
Status
Deferred
Published
Jul 14, 2026, 9:16 PM
Modified
Oct 24, 2026, 9:10 PM