CVE-2026-94627

Sažetak

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.

Reference

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#L1978-L1989
https://github.com/vllm-project/vllm/pull/49796
https://www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collision

CVSS

Base:	7.5
Impact:	3.6
Exploitability:	3.9

Pristup

Vektor	Složenost	Autentikacija
NETWORK	LOW	NONE

Impact

Povjerljivost	Cjelovitost	Dostupnost
NONE	NONE	HIGH

CVSS vektor

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

Zadnje važnije ažuriranje

21-09-2026 - 22:17

Objavljeno

21-09-2026 - 22:17