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.
Metrics
CVSS 3.1 6.2/10
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| NVIDIA | TensorRT-LLM | >= 0.0, <= v1.3.0 rc14 |
References
Timeline
- Published
- Jul 14, 2026
- Last modified
- Oct 24, 2026
- NVD status
- Deferred