Denial of Service Vulnerability in NVIDIA TensorRT-LLM's Inference API
CVE-2026-24271
6.2MEDIUM
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