NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.
Exploitability
AV:LAC:LPR:NUI:NScope
S:UImpact
C:NI:NA:H6.2/CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HOther