CVE-2026-94627 — vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision
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 disaggre…
Published: 2026-09-21 · CVSS: 8.7 · CVSS 4.0
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7