Allocation of Resources Without Limits or Throttling Affecting vllm package, versions [0.7.3,0.31.0)
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-21347787
- published21 Oct 2026
- disclosed21 Oct 2026
- creditChedrian07
Introduced: 21 Oct 2026
NewCVE-2026-114055 (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 unvalidated per-request mm_processor_kwargs forwarded through the multimodal processing pipeline. Remote clients can supply arbitrary values for resource-sensitive parameters such as image size, patch count, crop count, or frame count, which are forwarded without restriction to Hugging Face and custom image/video processor constructors including those in Isaac, InternVL, H2OVL, Step3VL, NemotronVL, and other multimodal processors. A single request targeting an upscaling processor can force a memory allocation large enough to exhaust CPU or GPU memory and terminate the API server or worker process, denying availability to all users of the shared service instance.