Homepage

Allocation of Resources Without Limits or Throttling Affecting vllm-openai-cuda-12.9 package, versions <0.19.0-r0

Severity

 Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

EPSS
0.46% (39th 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-CHAINGUARDLATEST-VLLMOPENAICUDA129-16000013
  • published13 Apr 2026
  • disclosed6 Apr 2026
Report a new vulnerability Found a mistake?

Introduced: 6 Apr 2026

CVE-2026-34755  (opens in a new tab)
CWE-770  (opens in a new tab)

How to fix?

Upgrade Chainguard vllm-openai-cuda-12.9 to version 0.19.0-r0 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm-openai-cuda-12.9 package and not the vllm-openai-cuda-12.9 package as distributed by Chainguard. See How to fix? for Chainguard relevant fixed versions and status.

vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.