Skip to content
OpenAdvisories
Medium WID-SEC-2026-2176 4 CVEs

vllm: Mehrere Schwachstellen ermöglichen Denial of Service

Published Jul 1, 2026 · Updated Oct 26, 2026 · Revision 7 · de-DE

Vendor: Red Hat Product: Enterprise Linux Platform: Linux

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 4

  • High 8.7
    CVE-2026-55574

    vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation ti…

    vLLM vLLM vllm PyPI
  • High 7.5
    CVE-2026-54234

    vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size…

    vLLM vLLM vllm PyPI
  • High 7.1
    CVE-2026-55514

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

    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 serve…

    vLLM vLLM vllm PyPI
  • Medium 6.5
    CVE-2026-55646

    vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

    vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the do…

    vLLM vLLM vllm PyPI

Revision history

  1. #7

    Neue Updates von Red Hat aufgenommen

  2. #6

    Neue Updates von Red Hat aufgenommen

  3. #5

    Neue Updates von Red Hat aufgenommen

  4. #4

    Neue Updates von Red Hat aufgenommen

  5. #3

    Neue Updates von Red Hat aufgenommen

  6. #2

    Referenz(en) aufgenommen: EUVD-2026-41914, EUVD-2026-41921, EUVD-2026-41924, EUVD-2026-41925

  7. #1

    Initiale Fassung

References