CVE-2026-24158 Denial of service in Triton Inference Server

What is CVE-2026-24158?

CVE-2026-24158 is a high-severity denial of service vulnerability in Nvidia Triton Inference Server, published on 24 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service.

Weakness: CWE-789

Which versions are affected by CVE-2026-24158?

It affects 1 product.

Products include Nvidia Triton Inference Server.

How do I fix CVE-2026-24158?

Apply the vendor's patch.

Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.

Is CVE-2026-24158 being exploited?

There is no known exploitation of CVE-2026-24158 in the wild and no public exploit code.

Other vulnerabilities in Nvidia Triton Inference Server

• CVE-2026-47627 Path traversal in Triton Inference Server Critical 9.8
• CVE-2026-24207 Auth bypass in Triton Inference Server Critical 9.8
• CVE-2025-23316 Command injection in Triton Inference Server Critical 9.8
• CVE-2025-23310 Memory corruption in Triton Inference Server Critical 9.8
• CVE-2025-23311 Memory corruption in Triton Inference Server Critical 9.8

All Nvidia Triton Inference Server vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-272x-gpf6-6c9f, MINI-wqfr-wx22-rmrg.