CVE-2026-24271 PUBLISHED

Assigner: nvidia
Reserved: 21.01.2026 Published: 14.07.2026 Updated: 15.07.2026

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.

Metrics

CVSS Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS Score: 6.2

Product Status

Vendor NVIDIA
Product TensorRT-LLM
Versions Default: unaffected
  • affected from 0.0 to v1.3.0 rc14 (incl.)

References

Problem Types

  • CWE-770 Allocation of Resources Without Limits or Throttling CWE

Impacts

  • Denial of Service