Allocation of Resources Without Limits or Throttling Affecting vllm package, versions [,0.25.0)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
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-19883612
- published17 Sept 2026
- disclosed16 Sept 2026
- creditRex Liu, Juan Pérez de Algaba
Introduced: 16 Sep 2026
NewCVE-2026-69147 (opens in a new tab)How to fix?
Upgrade vllm to version 0.25.0 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.merge_kwargs() in vllm/multimodal/media/video.py, where a request-level media_io_kwargs parameter can specify a GPU video backend (e.g. pynvvideocodec) that was not configured or VRAM-reserved at engine startup. An authenticated attacker can submit requests that trigger unreserved CUDA context and decoder-surface allocations, starving the KV cache and crashing the inference server.
Note: This is only exploitable when the server has not configured a GPU video backend at startup, but the attacker supplies one via per-request media_io_kwargs.