CVE-2026-34755: vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

Severity: medium (CVSS 6.5 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.5% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-04-06 · updated 2026-08-25
Weakness: CWE-770

Description

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.

Affected products

vllm-project vllm: from 0.7.0 before 0.19.0 — fixed in 0.19.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.19.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-34755 or the next vulnerability affects your stack