6.5Medium

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

vllm-project vllm Published: (24 days ago)

Description

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.

Weakness (CWE): CWE-400CWE-770CWE-834

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
vllm-project vllm >= 0.19.0, < 0.32.0

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.19.0 < 0.32.0