p PatchFirst

CVE-2026-115911

CVE-2026-115911 · vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

Cette page présente des faits issus de sources publiques. Consultez l’avis original avant toute mise à jour.

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.

CVSS 6.5 · Moyenne · EPSS 0,3% · Correctif disponible

Publication
Mise à jour

Pile logicielle: python

Produits et versions concernés

  • vllm

    Versions du logiciel
    • >= 0.19.0, < 0.32.0: Concernée

    Aucun correctif publié

  • vllm PyPI

    Versions du logiciel
    • 0.19.0
    • 0.19.1
    • 0.20.0
    • 0.20.1
    • 0.20.2
    • 0.21.0
    • 0.22.0
    • 0.22.1
    • 0.23.0
    • 0.24.0
    • 0.25.0
    • 0.25.1
    • 0.26.0
    • 0.27.0
    • 0.27.1
    • 0.28.0
    • 0.29.0
    • 0.30.0
    • 0.31.0
    Plages de versions concernées
    • ECOSYSTEM: ≥ 0.19.0, < 0.32.0

    Mettez à jour vers 0.32.0

Sources originales

Vérifiez votre serveur →