CVE-2026-94625 PUBLISHED

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 480 seconds while health checks continue returning success.

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

• Pull Request #51236
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1234-L1242
• https://github.com/vllm-project/vllm
• VulnCheck Advisory: vLLM through 0.29.0 Resource Exhaustion via Ownerless Mooncake Transfer Placeholders

• Missing Release of Resource after Effective Lifetime CWE