Skip to content
fr Sign in
6.5 Medium

CVE-2026-34755 vLLM is an inference and serving engine for large language models (LLMs)

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 and versions

Product Affected versions Fixed in
vllm 0.7 0.7.0 → < 0.19.0 0.19.0
Red Hat AI Inference Server Versions not published
Red Hat Enterprise Linux AI (RHEL AI) 3 Versions not published
Red Hat OpenShift AI (RHOAI) Versions not published
Red Hat AI Inference Server 3.2 1782951244 earliest → < 1782951244 1782951244
Red Hat AI Inference Server 3.4 1787151774 earliest → < 1787151774 1787151774
Red Hat Enterprise Linux AI 3.4 1787244006 earliest → < 1787244006 1787244006

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High
Track this CVE