vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.loadbase64() 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 numframes 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.
{
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/34xxx/CVE-2026-34755.json",
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-770"
]
}