High severity7.5NVD Advisory· Published Sep 17, 2026
CVE-2026-93436
CVE-2026-93436
Description
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
1Patches
Vulnerability mechanics
References
3News mentions
0No linked articles in our index yet.