vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision (CVE-2026-94627) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-94627

vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

Answer in brief

CVE-2026-94627 records a Unknown severity vulnerability in vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Sep 21, 2026Updated Sep 21, 2026Source checked Sep 22, 2026First seen by HOL Sep 21, 2026Material review Sep 21, 2026

Upstream Advisory

Key facts

Risk: Unknown severitySource severity not reported
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
vllm-project/vllmgeneric	0	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for vllm-project/vllm.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Sep 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Sep 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Sep 21, 2026

Sources and claim methodology

Upstream source 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.

Quoted source text, attributed separately from HOL analysis.