Track vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
6.5

NVIDIA Triton Inference Server: Large Model File Causes Server Crash

CVE-2024-53880 · published 1 year ago
Summary

A big model file can cause NVIDIA Triton Inference Server to crash, making it unavailable. This is a serious issue because it could prevent the server from working at all. To fix this, users should update to the latest version of NVIDIA Triton Inference Server to ensure they have the latest security patches.

What to do
  • Update nvidia triton_inference_server to version 24.12 or later.
Affected software
VendorProductAffected versions
nvidia triton_inference_server < 24.12
cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*
Original advisory text
NVIDIA Triton Inference Server contains a vulnerability in the model loading API, where a user could cause an integer overflow or wraparound error by loading a model with an extra-large file size t...
NVIDIA Triton Inference Server contains a vulnerability in the model loading API, where a user could cause an integer overflow or wraparound error by loading a model with an extra-large file size that overflows an internal variable. A successful exploit of this vulnerability might lead to denial of service.
References
Fix within
Internet-facing 60 days
Internal At next upgrade
  • Not known to be exploited
  • Needs hands-on effort to exploit (estimated)
  • Gives an attacker partial control (estimated)
Severity
6.5 Medium
Exploitation
<1% chance of attack within 30 days
Type
CWE-190Integer Overflow
Timeline
Published12 Feb 2025
Updated4 Nov 2026
First seen7 Mar 2026
Sources
CVE-2024-53880 · NVD
Track software like this
Free during beta