CVE-2026-24271CWE-770
NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits…
Medium · published July 14, 2026
What it is
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.
The record
Technical detail
- CVSS v3.1
- 6.2 · MEDIUM
- Vector
- CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CVSS v4.0
- Not supplied
- EPSS
- 0.00160 · 4.9th percentile
- Weakness
- CWE-770 · Allocation of Resources Without Limits or Throttling
- Published
- 2026-07-14T20:09Z
EPSS history
Timeline