GPU VulnDB

Database/NVIDIA / GPU stack

Triton Inference Server: DoS via memory exhaustion on malformed input

CVE-2026-24146NVIDIA / GPU stackcurated

Impact

DoS via memory exhaustion on malformed input

Who can reach it

Any client of the inference endpoint

What to do

Upgrade Triton; redeploy serving images; add request limits

References

https://nvd.nist.gov/vuln/detail/CVE-2026-24146https://github.com/NVIDIA/product-security/tree/main/2026/5816

This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.