MEDIUM
CVE-2026-94625
CVSS
5.3
Description
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.
Weakness (CWE)
CWE-772
References
https://github.com/vllm-project/vllm
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/pull/51236
https://www.vulncheck.com/advisories/vllm-through-0.29.0-resource-exhaustion-via-ownerless-mooncake-transfer-placeholders
Base CVE data derived from NVD (public domain). Enrichment by
dbcve.org
(CC-BY-4.0). Fetched via API.