Published: September 21, 2026 | Last Modified: September 21, 2026
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.
Exploitation Probability (EPSS): Low — 0.45% (38th percentile)
Low exploitation probability based on current threat landscape data. Standard patching timeline is appropriate.
This analysis is generated by Ghostwire from NVD, CISA KEV, EPSS, and open-source intelligence data. Verify findings through primary sources before acting.