CVE-2026-94627: 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 GP
What it means
NIST National Vulnerability Database ha pubblicato CVE-2026-94627. La rilevanza va confermata rispetto alle tecnologie effettivamente in uso.
Why it matters
Il segnale diventa operativo solo se prodotto, versione o servizio sono presenti nel perimetro.
Recommended actions
- Confermare l'applicabilita consultando la fonte ufficiale e l'inventario asset.
- Pianificare mitigazione o aggiornamento secondo criticita e rischio di interruzione.
Translation in progress
The official content is available in the original language. The Italian version will be published once automated checks are complete.
Text acquired from the source
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
- NIST National Vulnerability Database
- Publishing entity
- NIST National Vulnerability Database
- Entity type
- National authority
- Area
- North America · US
- Original language
- en · translation in preparation
- Publication
- 22/09/2026 00:17
- CVE
- CVE-2026-94627
- Classification
- High
- Stated country
- US
Affected products and versions
The official sources queried do not yet expose a list of affected versions. No automatic inference is made.