CVE-2026-55514
vLLM denial of service via prompt embeds on M-RoPE models
EPSS 0.37%
描述
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.
如何修補 CVE-2026-55514
要修補 CVE-2026-55514,請將受影響套件升級到下列已修補版本。
- PyPI/vllm—升級至 0.24.0 或更新版本
CVE-2026-55514 正在被利用嗎?
低 — EPSS 為 0.4%,目前沒有觀察到大規模利用活動。
受影響套件(1)
- >= 0.12.0, < 0.24.0
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 4.0 | — | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N |