Allocation of Resources Without Limits or Throttling Affecting vllm package, versions [0.16.0,0.32.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Allocation of Resources Without Limits or Throttling vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-VLLM-21755381
- published27 Oct 2026
- disclosed26 Oct 2026
- creditRex Liu
Introduced: 26 Oct 2026
NewCVE-2026-115918 (opens in a new tab)How to fix?
Upgrade vllm to version 0.32.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the chat template rendering path in the Responses API endpoint, where a request-supplied chat_template in chat_template_kwargs is rendered without a fuel budget or timeout guard. An authenticated attacker can submit a chat template containing unbounded loops or expensive string operations, exhausting CPU resources and crashing the server.
Note: This is only exploitable via the Responses API endpoint when the server is started with --trust-request-chat-template, as the Chat Completions endpoint already rejected request-supplied chat templates without that flag.