CVE-2026-34755— vLLM 安全漏洞

vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

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.

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

不加限制或调节的资源分配

vLLM 安全漏洞

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.7.0至0.19.0之前版本存在安全漏洞，该漏洞源于VideoMediaIO.load_base64方法未强制帧数限制，可能导致内存耗尽和服务器崩溃。

N/A

N/A