CVE-2026-55514highCWE-617

vLLM denial of service via prompt embeds on M-RoPE models

21Vexday Risk Score

Sin señal de explotación. Ningún artefacto público de explotación conocido hasta ahora.

ssvc Trackcvss 7.1epss 0.4%

probabilidad de explotación

0.4%top 70% de las CVE

explotación observada

noninguna fuente lo reporta

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.

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

Productos afectados

vllm-project · vllm

Referencias

https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65 https://github.com/vllm-project/vllm/pull/45252 https://github.com/vllm-project/vllm/releases/tag/v0.24.0 https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g