CVE-2026-55514
vllm-project vllm 취약점
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.
- 대응 우선순위
- 점검
- CVSS
- 7.1
- EPSS
- 0.37% 백분위 29.6% · 2026.07.28 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.07