CVE-2026-94627 PUBLISHED

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.

• Mingkai Yu finder
• Jiapeng Li finder
• Jiajia Liu finder

• Pull Request #49796
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1978-L1989
• https://github.com/vllm-project/vllm
• VulnCheck Advisory: vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

• Missing Release of Memory after Effective Lifetime CWE