Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | <= 0.29.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllmProduct
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kProduct
- https://github.com/vllm-project/vllm/pull/49796Issue TrackingPatch
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mThird Party Advisory
FAQ
What is CVE-2026-94627?
CVE-2026-94627 is a vulnerability with a CVSS score of 7.5 (HIGH). 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. Atta...
How severe is CVE-2026-94627?
CVE-2026-94627 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-94627?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.