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 products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | ≤ 0.29.0 | — |
Advisories 1
- WID-SEC-2026-3507 vllm: Mehrere Schwachstellen ermöglichen Denial of Service BSI CERT-Bund (WID) · Nov 9, 2026
References
- Pull Request #49796 issue-tracking patch
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989 technical-description
- https://github.com/vllm-project/vllm product
- VulnCheck Advisory: vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision third-party-advisory