MEDIUM 6.9 NVD
CVE-2026-78684
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 ac
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.
References
- https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419
- https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq
- https://www.vulncheck.com/advisories/vllm-before-denial-of-service-via-deepstream-backend
This medium severity vulnerability with a CVSS score of 6.9 was published on 2026-08-25 via NVD.
vulnfeed aggregates 12116 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.