CVE-2026-94625

medium

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.

References

https://www.vulncheck.com/advisories/vllm-through-0.29.0-resource-exhaustion-via-ownerless-mooncake-transfer-placeholders

https://github.com/vllm-project/vllm/pull/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

Details

Source: Mitre, NVD

Published: 2026-09-21

Updated: 2026-09-21

Risk Information

CVSS v2

Base Score: 5

Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:P

Severity: Medium

CVSS v3

Base Score: 5.3

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

Severity: Medium

CVSS v4

Base Score: 6.9

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

Severity: Medium