Allocation of Resources Without Limits or Throttling Affecting vllm-cu129 package, versions <0.24.0-r0


Severity

Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

EPSS
0.66% (50th 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-VLLMCU129-19889342
  • published18 Sept 2026
  • disclosed16 Sept 2026

Introduced: 16 Sep 2026

NewCVE-2026-57173  (opens in a new tab)
CWE-770  (opens in a new tab)

How to fix?

Upgrade Minimos:latest vllm-cu129 to version 0.24.0-r0 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm-cu129 package and not the vllm-cu129 package as distributed by Minimos. See How to fix? for Minimos:latest relevant fixed versions and status.

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.