Description
vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causing partial denial of service for concurrent requests.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | < 0.27.0 | 0.27.0 |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | < 0.27.0 | 0.27.0 | PYSEC-2026-4003 |
Advisories 1
- WID-SEC-2026-2739 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Oct 29, 2026
References
- GitHub Security Advisory (GHSA-cqm8-jxg6-fqfq) vendor-advisory
- Patch Commit patch
- VulnCheck Advisory: vLLM before 0.27.0 Denial of Service via DeepStream Backend third-party-advisory