Threats·Cloud & SaaSBreakingvLLM Continuous Batching Engine Vulnerability Enables Cross-Tenant KV-Cache Extraction and Host Memory Corruption (CVE-2026-72110)vLLM issues critical advisory CVE-2026-72110 for its continuous batching inference engine, patching a PagedAttention memory calculation bug that leaked LLM KV-cache tokens.CST Newsroom11 Oct 20268 min read