8.7
Élevée
CVE-2026-94627 vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child…
Description
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.
Produits et versions touchés
| Produit | Versions touchées | Corrigé en |
|---|---|---|
| vllm 0.29 | premières → 0.29.0 | Pas de correctif indiqué |
Références
- Pull Request #49796 github.com
- github.com github.com
- github.com github.com
- VulnCheck Advisory: vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision www.vulncheck.com
Chronologie
- Publiée
- Dernière modification
Autres CVE de vllm
Les 121 CVE de vllm →
CVE-2026-115918
vLLM is an inference and serving engine for large language models
6.5
Moyenne
CVE-2026-115917
vLLM is an inference and serving engine for large language models
3.4
Faible
CVE-2026-115916
vLLM is an inference and serving engine for large language models
6.5
Moyenne
CVE-2026-115915
vLLM is an inference and serving engine for large language models
8.1
Élevée