CVE-2026-94627
⚠️ highSummary
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.
CVSS Score
7.5
High
EPSS Score
0.6
Exploit Probability
Published Date
2026-09-21
First Seen: 2026-09-24
📊 Relative Risk Intelligence
This CVE is Moderate Risk - more severe than 67.7% of all 361,628 vulnerabilities in our database.
#116,659
Above average severity
Severity Percentile
🎯 CISA SSVC Assessment Updated: Sep 22, 2026
🔍 Exploitation Status
None
No known exploits
⚙️ Automatable
YES
Can be exploited automatically
💥 Technical Impact
Partial
Limited system impact
🏆 Discovered By
Mingkai Yu
Jiapeng Li
Jiajia Liu
SSVC data provided by
CISA
Last Modified
2026-09-22
Source
NVD 🔗
CVSS Vector 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CWE IDs (Weakness Types)