Denial of Service Vulnerability in NVIDIA TensorRT-LLM's Inference API
CVE-2026-24271

6.2MEDIUM

Key Information:

Vendor

Nvidia

Vendor
CVE Published:
14 July 2026

What is CVE-2026-24271?

NVIDIA TensorRT-LLM contains a vulnerability in its OpenAI-compatible inference API that allows attackers to allocate GPU resources without any limits or throttling. This flaw can be exploited to create a denial of service condition, hindering the performance and availability of the affected product.

Affected Version(s)

TensorRT-LLM 0.0

References

CVSS V3.1

Score:
6.2
Severity:
MEDIUM
Confidentiality:
None
Integrity:
None
Availability:
None
Attack Vector:
Local
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.