VYPR
Medium severity6.5OSV Advisory· Published Jul 6, 2026· Updated Jul 7, 2026

CVE-2026-55514

CVE-2026-55514

Description

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 packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
vllmPyPI
>= 0.12.0, < 0.24.00.24.0

Affected products

3
  • Vllm/VllmOSV3 versions
    (expand)+ 2 more
    • (no CPE)
    • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*range: >=0.12.0,<0.24.0
    • (no CPE)range: 0.12.0 <= x < 0.24.0

Patches

Vulnerability mechanics

References

7

News mentions

1