CVEvulnerability
CVE-2026-115911
6.5 MEDIUM
Official page ↗
- Status
- Analyzed
- Published
- 2026-10-26
- Last modified
- 2026-10-28
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-400, CWE-770, CWE-834
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.
Affected configurations
• vllm vllm (>= 0.19.0 < 0.32.0)
Related
References
- https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134 Patch
- https://github.com/vllm-project/vllm/pull/50300 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-542m-9234-8gvf Patch, Vendor Advisory