vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attacker…
Low CVSS 3.7
Summary
vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits and exhaust unaccounted GPU memory.
In-depth triage
No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).
Sources
- NVD DATABASE
Original Links
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j682-9xp5-rrf3
- https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-limit-bypass-via-sampler-subclass
Timeline
- nvd_ingest NVD