CVE-2026-78684
Description
A flaw was found in vLLM. Unauthenticated attackers can exploit this vulnerability by activating the DeepStream backend during a request. This allows them to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, leading to a partial denial of service for concurrent requests.
Statement
A flaw was found in the vLLM inference engine, which is shipped in Red Hat AI Inference Server 3 and Red Hat Enterprise Linux AI (RHEL AI) container images. vLLM does not classify DeepStream as a GPU backend, and its decode path omits pixel-limit enforcement, so an unauthenticated remote client can activate the DeepStream backend during a request to initialize the process-wide GPU decode pool and submit video that bypasses resource controls. This can exhaust GPU decode resources and cause a partial denial of service for concurrent requests; confidentiality and integrity are not impacted. Because the flaw is rated Moderate with availability-only impact, the fix is deferred to a future update of the affected products; until then, the residual risk is that an unauthenticated client can degrade service for concurrent requests on affected vLLM deployments. The Red Hat severity (CVSS 5.3, Moderate) is consistent with the upstream CVSS v3 assessment.
Mitigation
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
The following CVSS metrics and score provided are preliminary and subject to review.
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 5.3 | N/A | 5.3 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | None | N/A | None |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | None | N/A | None |
| Integrity Impact | None | N/A | None |
| Availability Impact | Low | N/A | Low |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
cve.org: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Understanding the Weakness (CWE)
Availability
Technical Impact: DoS: Resource Consumption (CPU); DoS: Resource Consumption (Memory); DoS: Resource Consumption (Other)
When allocating resources without limits, an attacker could prevent other systems, applications, or processes from accessing the same type of resource. It can be easy for an attacker to consume many resources by rapidly making many requests or causing larger resources to be used than is needed.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
