VYPR
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

1

Patches

Vulnerability mechanics

References

3

News mentions

0

No linked articles in our index yet.