CVE-2026-78684

Published: Ago 25, 2026 Last Modified: Ago 25, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 6,9
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
MEDIUM 5,3
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Scope: unchanged
Confidentiality: none
Integrity: none
Availability: low

Description

AI Translation Available

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.

400

Uncontrolled Resource Consumption

Draft
Common Consequences
Security Scopes Affected:
Availability Access Control Other
Potential Impacts:
Dos: Crash, Exit, Or Restart Dos: Resource Consumption (Cpu) Dos: Resource Consumption (Memory) Dos: Resource Consumption (Other) Bypass Protection Mechanism Other
Applicable Platforms
Technologies: Not Technology-Specific, AI/ML
View CWE Details
https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba1…
https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq
https://www.vulncheck.com/advisories/vllm-before-denial-of-service-via-deepstre…