Allocation of Resources Without Limits or Throttling Affecting vllm package, versions [0.18.0,0.31.0)
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-21707817
- published25 Oct 2026
- disclosed25 Oct 2026
- credittonghuaroot (童话)
Introduced: 25 Oct 2026
NewCVE-2026-116179 (opens in a new tab)How to fix?
Upgrade vllm to version 0.31.0 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 VideoMediaIO.load_base64 in the multimodal media handling path, where request-level media_io_kwargs values are passed to VideoMediaIO without restricting the num_frames parameter. An attacker can set num_frames to -1 in a request's media_io_kwargs.video, causing the unlimited decoding branch to be selected, which splits and decodes every frame of a large inline video/jpeg payload. This causes the API frontend to allocate a multi-gigabyte frame array via numpy.stack, exhausting memory and crashing the serving process.