Inefficient Algorithmic Complexity Affecting vllm package, versions [0.8.0,0.8.5)
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 applications- Snyk IDSNYK-PYTHON-VLLM-10042526
- published7 May 2025
- disclosed30 Apr 2025
- creditkexinoh, d3do-23, zhongyuan chen
Introduced: 30 Apr 2025
NewCVE-2025-46560 (opens in a new tab)How to fix?
Upgrade vllm to version 0.8.5 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 Inefficient Algorithmic Complexity through the input_processor_for_phi4mm function. An attacker can cause the application to consume excessive resources and become unresponsive by submitting specially crafted inputs with many placeholders triggering extensive computational operations.