Medium [CVE-2026-78684] Denial of Service via DeepStream backend resource control bypass.
This medium-severity Red Hat Linux advisory covers CVE-2026-78684 affecting Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI).
Android app · Google Play
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 32 official vendor sources and 160+ reviewed platform categories.
Summary
vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causing partial denial of service for concurrent requests.
A flaw was found in vLLM. Red Hat severity: Moderate — CVSS 5.3 (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L).
Weakness: CWE-770. Affected Red Hat products: Red Hat AI Inference Server; Red Hat Enterprise Linux AI (RHEL AI) 3; Red Hat OpenShift AI (RHOAI).
Red Hat does not currently list a fixing RHSA for this CVE.
- < 0.27.0
Official advisory · high-confidence parse· fetched 41 minutes ago·verify at source
Fixed versions
No fixed release is recorded yet. That does not prove no patch exists — confirm against the vendor advisory.
Official advisory · high-confidence parse· fetched 41 minutes ago·verify at source
Mitigation
The source record does not include mitigation steps. That is not a statement that no fix exists — read the vendor advisory below for the authoritative guidance.
Official advisory · high-confidence parse· fetched 41 minutes ago·verify at source
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.