CVE-2026-94627
HIGH
7.5
Our Analysis: Environment Specific
Our model has classified this vulnerability as relevant to Environment Specific Systems, helping your team prioritize efforts effectively.
Published Date
September 21, 2026
Last Modified
September 21, 2026
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Description
vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts, causing orphaned KV cache blocks to accumulate until process restart and eventually preventing legitimate requests from executing.