Medium severity · published Aug 25, 2026
CVE-2026-78684
vLLM before 0.27.0 Denial of Service via DeepStream Backend
5.3
CVSS
0.6%
EPSS
No
On KEV
Description
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
Low
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 49% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
before 0.27.0 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-78684
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-78684
Patch
https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419
Vendor Advisory
https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq
Third Party Advisory
https://www.vulncheck.com/advisories/vllm-before-denial-of-service-via-deepstream-backend
More from vllm
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints
9.1
CVE-2026-48746
vLLM: OpenAI auth bypass