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.
{
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/78xxx/CVE-2026-78684.json",
"cwe_ids": [
"CWE-400"
],
"cna_assigner": "VulnCheck"
}