Skip to content
OpenAdvisories
Medium WID-SEC-2026-3754 5 CVEs

vllm: Mehrere Schwachstellen ermöglichen Denial of Service

Published Oct 5, 2026 · Updated Oct 5, 2026 · de-DE

Summary

Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.

Product

Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).

Vulnerabilities 5

  • Medium 6.5
    CVE-2026-105753

    vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core

    vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiv…

    vLLM vLLM vllm PyPI
  • Medium 6.5
    CVE-2026-105756

    vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

    vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCa…

    vLLM vLLM vllm PyPI
  • Medium 5.9
    CVE-2026-105759

    vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service)

    vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker …

    vLLM vLLM vllm PyPI
  • Medium 5.3
    CVE-2026-105758

    vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

    vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields with…

    vLLM vLLM vllm PyPI
  • Medium 5.3
    CVE-2026-105760

    vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

    vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work cei…

    vLLM vLLM vllm PyPI

Revision history

  1. #1

    Initiale Fassung

References