CVEvulnerability
CVE-2026-94627
8.7 HIGH
Official page ↗
- Status
- Analyzed
- Published
- 2026-09-21
- Last modified
- 2026-09-29
- Assigner
- [email protected]
- CVSS 4.0 ([email protected])
- 8.7 HIGH — 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
- CVSS 3.1 ([email protected])
- 7.5 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-401
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.
Affected configurations
• vllm vllm (<= 0.29.0)
Related
Weakness · CWE (1)
- CWE-401 Missing Release of Memory after Effective Lifetime weakness
References
- https://github.com/vllm-project/vllm Product
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989 Product
- https://github.com/vllm-project/vllm/pull/49796 Issue Tracking, Patch
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision Third Party Advisory