CVE-2026-55514: Vllm

Medium severity, CVSS 6.5. EPSS: 0.7% chance of exploitation in the next 30 days.

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

Affected products

• Vllm Vllm: from 0.12.0, before 0.24.0 (fixed in 0.24.0)

Published 2026-07-06. Last modified 2026-07-07.