p PatchFirst

CVE-2025-62372

CVE-2025-62372 · vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

This page contains facts from public vulnerability sources. Check the original advisory before updating.

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

CVSS 8.3 · High · EPSS 0.4% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.5.5, < 0.11.1: Affected

    No fix published

  • vllm PyPI

    Versions
    • 0.10.0
    • 0.10.1
    • 0.10.1.1
    • 0.10.2
    • 0.11.0
    • 0.5.5
    • 0.6.0
    • 0.6.1
    • 0.6.1.post1
    • 0.6.1.post2
    • 0.6.2
    • 0.6.3
    • 0.6.3.post1
    • 0.6.4
    • 0.6.4.post1
    • 0.6.5
    • 0.6.6
    • 0.6.6.post1
    • 0.7.0
    • 0.7.1
    • 0.7.2
    • 0.7.3
    • 0.8.0
    • 0.8.1
    • 0.8.2
    • 0.8.3
    • 0.8.4
    • 0.8.5
    • 0.8.5.post1
    • 0.9.0
    • 0.9.0.1
    • 0.9.1
    • 0.9.2
    Affected ranges
    • ECOSYSTEM: ≥ 0.5.5, < 0.11.1

    Update to 0.11.1

Original sources

Check your server →