LLMHigh

CVE-2026-115911: vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authent…

Occurred: Oct 26, 2026
Published: Oct 26, 2026
Source: NVD CVE

Summary

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.

Classification

Category confidence: 95%

Severity confidence: 90%

Rationale: CVE describes a denial-of-service vulnerability in vLLM LLM serving engine allowing resource exhaustion via malicious chat templates.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source

Summary

Tags

Classification