Resource Exhaustion Affecting vllm-wheels package, versions *


Severity

Recommended
0.0
high
0
10

Snyk's Security Team recommends NVD's CVSS assessment. Learn more

Threat Intelligence

EPSS
0.2% (9th 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 IDSNYK-MINIMOSLATEST-VLLMWHEELS-20147085
  • published26 Sept 2026
  • disclosed12 Sept 2026

Introduced: 12 Sep 2026

NewCVE-2026-90554  (opens in a new tab)
CWE-400  (opens in a new tab)

How to fix?

There is no fixed version for Minimos:latest vllm-wheels.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm-wheels package and not the vllm-wheels package as distributed by Minimos. See How to fix? for Minimos:latest relevant fixed versions and status.

vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.

CVSS Base Scores

version 3.1