CVE-2026-126394: vLLM resource exhaustion in OpenCVDynamicOpenPanguVideoBackend via num_frames

Summary

vLLM 0.30.0 before 0.31.0 has a resource exhaustion flaw in OpenCVDynamicOpenPanguVideoBackend, which uses the request-controlled num_frames value without an effective ceiling. An unauthenticated attacker can send a request to /v1/chat/completions or /tokenize that selects the openpangu video_backend with a very large num_frames, forcing np.linspace allocations and CPU work that OOM-kill the API server.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Topics

• Inference infrastructure

Related items

• MediumCVE-2026-126399: vLLM resource exhaustion via video frame limit bypass in chat completionsSimilar attack · NVD/CVE Database
• MediumCVE-2026-126398: vLLM reachable assertion crash in GPUModelRunner via embeddings-only requestsSimilar attack · NVD/CVE Database
• HighCVE-2026-126397: vLLM denial of service via unbounded max_patches in multimodal preprocessingSimilar attack · NVD/CVE Database
• MediumCVE-2026-126396: vLLM resource exhaustion in MiniMax M3 VL video processor via min_pixelsSimilar attack · NVD/CVE Database
• MediumEndor Labs’ AI SAST Finds Zero Day Memory-Amplification DoS in Anthropic’s buffa library | Endor LabsSimilar attack · Endor Labs Blog