High severity7.5NVD Advisory· Published Sep 21, 2026

CVE-2026-94627

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Vllm/Vllmreferences2 versions
(expand)+ 1 more
- (no CPE)
- (no CPE)range: <=0.29.0

Patches

Vulnerability mechanics

References

github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.pynvd
github.com/vllm-project/vllm/pull/49796nvd
www.vulncheck.com/advisories/vllm-through-0.29.0-gpu-kv-cache-leak-via-mooncake-transfer-id-collisionnvd

News mentions

No linked articles in our index yet.

cvss	0.488
epss	0.000
exploit	0.000
kev	0.000
patch	-0.070
ransomware	0.000