vLLM
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 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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.7high · scored by CNA · CWE-401
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- <= 0.29.0
Mitigation
The record names no fix. Check the vendor advisory below.
References
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.