p PatchFirst

CVE-2026-115911

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

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. 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 · Medium · EPSS 0.3% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.19.0, < 0.32.0: Affected

    No fix published

  • vllm PyPI

    Versions
    • 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
    Affected ranges
    • ECOSYSTEM: ≥ 0.19.0, < 0.32.0

    Update to 0.32.0

Original sources

Check your server →