NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resourc

Versions reported by the vendor

Affected version ranges reported by the assigning authority (nvidia). Independent of NVD's CPE analysis and usually ahead of it.

• NVIDIA TensorRT-LLM

  • 0.0 and later · up to and including v1.3.0 rc14affected

Other highest-scoring records for the same primary product.

• CVE-2025-23254NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by loca
  35Monitor
• CVE-2026-24233NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, una
  33Monitor
• CVE-2026-47472NVIDIA TensorRT-LLM contains a vulnerability in its inter-process communication layer where an attacker with local same-user access could ca
  31Monitor
• CVE-2026-47471NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer o
  30Monitor
• CVE-2026-47473NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a write-what-where condition.
  29Monitor
• CVE-2026-24229NVIDIA TensorRT-LLM for Linux contains a vulnerability in the disaggregated orchestrator component, where an attacker could read, write, or
  29Monitor

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.