Evidence · DiggingBeagle record
vLLM video_backend override allows excessive frame sampling
Researcher advisory on request-selected OpenPangu backend and num_frames CPU/memory exhaustion.
- Published
- Nov 13, 2026
- Source role
- primary disclosure
Evidence record
Researcher advisory on request-selected OpenPangu backend and num_frames CPU/memory exhaustion.
Claim-level citations (2)
- supportsA client-supplied video sampling override could allocate excessive frames before model inference: In affected vLLM video-capable paths, a request could select the OpenPangu video backend and an extremely large num_frames value. Timestamp generation and list construction ran in Python before inference-level controls could bound the work. The researcher reproduced high CPU and memory consumption on a bounded test. A patch disables untrusted request-level multimodal overrides unless an operator explicitly enables their trusted mode. The larger projected allocations in the report were not all executed.
vLLM GHSA-894j-wg8m-63h8, video_backend OpenPangu override and num_frames request reproduction
- supportsA client-supplied video sampling override could allocate excessive frames before model inference: This is an admission and resource-budget failure, not a demonstrated GPU memory escape or a real production outage. Turning the trusted-override flag back on requires independent resource caps for the underlying sampler. The evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.
Primary disclosure: results, scope and limitations