LLM frameworks · vLLM project
vLLM
High-throughput LLM inference server.
3Advisories
3critical
0high
0medium
2026-02-02Latest
Timeline · advisories per quarter
22025 Q2
12026 Q1
Named in sources
Reported for vLLM
01. CVE-2026-22778: vLLM has RCE In Video ProcessingvLLM has RCE In Video Processing. vLLM 2026-02-02 02. CVE-2025-47277: vLLM Allows Remote Code Execution via PyNcclPipe Communication ServicevLLM Allows Remote Code Execution via PyNcclPipe Communication Service. vLLM 2025-05-20 03. CVE-2025-32444: vLLM Vulnerable to Remote Code Execution via Mooncake IntegrationvLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. vLLM 2025-04-29
vLLM 2026-02-02 02. CVE-2025-47277: vLLM Allows Remote Code Execution via PyNcclPipe Communication ServicevLLM Allows Remote Code Execution via PyNcclPipe Communication Service. vLLM 2025-05-20 03. CVE-2025-32444: vLLM Vulnerable to Remote Code Execution via Mooncake IntegrationvLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. vLLM 2025-04-29