CVE-2026-94627

Severity CVSS v4.0:

HIGH

Type:

Unavailable / Other

Publication date:

21/09/2026

Last modified:

29/09/2026

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.

Impact

Vector 4.0

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N CVSS v4.0 Severity and Metrics:

Base Score: 8.70 HIGH
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Attack Vector (AV): Network
Attack Complexity (AC): Low
Attack Requirements (AT): None
Privileges Required (PR): None
User Interaction (UI): None
Confidentiality (VC): None
Integrity (VI): None
Availability (VA): High
Confidentiality (SC): None
Integrity (SI): None
Availability (SA): None

Base Score 4.0

8.70

Severity 4.0

HIGH

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H CVSS v3.1 Severity and Metrics:

Base Score: 7.50 HIGH
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Attack Vector (AV): Network
Attack Complexity (AC): Low
Privileges Required (PR): None
User Interaction (UI): None
Scope (S): Unchanged
Confidentiality (C): None
Integrity (I): None
Availability (A): High