Allocation of Resources Without Limits or Throttling Affecting vllm package, versions [0.30.0,0.31.0)


Severity

Recommended
0.0
medium
0
10

CVSS assessment by Snyk's Security Team. Learn more

Threat Intelligence

EPSS
0.32% (26th percentile)

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 Learn

Learn about Allocation of Resources Without Limits or Throttling vulnerabilities in an interactive lesson.

Start learning
  • Snyk IDSNYK-PYTHON-VLLM-22549747
  • published15 Nov 2026
  • disclosed13 Nov 2026
  • creditLucas Wang

Introduced: 13 Nov 2026

NewCVE-2026-126394  (opens in a new tab)
CWE-770  (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 OpenCVDynamicOpenPanguVideoBackend in vllm/multimodal/video.py, which derives its frame-index computation from the request-controlled num_frames field with no effective ceiling. An unauthenticated attacker can send a POST /v1/chat/completions or /tokenize request specifying "video_backend": "openpangu" with an arbitrarily large num_frames value, causing np.linspace to allocate memory proportional to that value and a Python list comprehension to walk every element inside the API-server process, ultimately OOM-killing the server.

References

CVSS Base Scores

version 4.0
version 3.1