CVE-2026-115911
Received
Received - Intake
vLLM Chat Template Rendering Denial of Service
Vulnerability report for CVE-2026-115911, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.
Publication date: 2026-10-26
Last updated on: 2026-10-26
Assigner: GitHub, Inc.
Description
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.
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| vllm-project | vllm | >= 0.19.0, < 0.32.0 |
Helpful Resources
Exploitability
CWE
KEV
| CWE ID | Description |
|---|---|
| CWE-400 | The product does not properly control the allocation and maintenance of a limited resource. |
| CWE-770 | The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated. |
| CWE-834 | The product performs an iteration or loop without sufficiently limiting the number of times that the loop is executed. |
