Bug 2560960 (CVE-2026-115911)

Summary: CVE-2026-115911 vllm: vLLM: Denial of Service via unbounded chat template rendering
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: unspecifiedCC: alinfoot, bbrownin, dtrifiro, mwoodson, weaton
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in vLLM. An authenticated remote attacker or a malicious model repository can cause a Denial of Service (DoS) by providing a specially crafted chat template. Because templates are rendered without execution timeouts or resource limits, processing the input can permanently block worker threads or exhaust system memory, rendering the service unresponsive or causing it to crash.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-10-26 17:03:47 UTC 
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.