p PatchFirst

CVE-2026-115911

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

Esta página presenta datos de fuentes públicas de vulnerabilidades. Consulta el aviso original antes de actualizar.

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 · Media · EPSS 0,3% · Corrección disponible

Publicación
Actualización

Pila tecnológica: python

Productos y versiones afectados

  • vllm

    Versiones
    • >= 0.19.0, < 0.32.0: Afectada

    Sin corrección publicada

  • vllm PyPI

    Versiones
    • 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
    Intervalos de versiones afectados
    • ECOSYSTEM: ≥ 0.19.0, < 0.32.0

    Actualiza a 0.32.0

Fuentes originales

Comprueba tu servidor →