hoch7.5
CVE-2026-94627
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 prefi…
Auswirkung
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.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, ohne Anmeldung, ohne Zutun eines Nutzers. Bei Erfolg: hohes Risiko für Ausfälle.
Betroffene Produkte · Vllm
| Produkt | Betroffene Versionen |
|---|---|
| Vllm | bis einschließlich 0.29.0 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- 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