6.5
Moyenne
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.
Produits et versions touchés
| Produit | Versions touchées | Corrigé en |
|---|---|---|
| vllm 0.7 | 0.7.0 → < 0.19.0 | 0.19.0 |
| Red Hat AI Inference Server | Versions non publiées | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Versions non publiées | |
| Red Hat OpenShift AI (RHOAI) | Versions non publiées | |
| Red Hat AI Inference Server 3.2 1782951244 | premières → < 1782951244 | 1782951244 |
| Red Hat AI Inference Server 3.4 1787151774 | premières → < 1787151774 | 1787151774 |
| Red Hat Enterprise Linux AI 3.4 1787244006 | premières → < 1787244006 | 1787244006 |
Références
- github.com github.com
Chronologie
- Publiée
- Dernière modification
Autres CVE de vllm
Les 121 CVE de vllm →
CVE-2026-115918
vLLM is an inference and serving engine for large language models
6.5
Moyenne
CVE-2026-115917
vLLM is an inference and serving engine for large language models
3.4
Faible
CVE-2026-115916
vLLM is an inference and serving engine for large language models
6.5
Moyenne
CVE-2026-115915
vLLM is an inference and serving engine for large language models
8.1
Élevée