NetSight
mittel6.5

CVE-2026-105753

vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core

Auswirkung

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.

Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, mit einem normalen Benutzerkonto, ohne Zutun eines Nutzers. Bei Erfolg: hohes Risiko für Ausfälle.

Betroffene Pakete

ÖkosystemPaketBetroffenBehoben in
pipvllm< 0.28.00.28.0

Betroffene Produkte · Vllm

ProduktBetroffene Versionen
Vllm
vor 0.28.0

Schwachstellenklasse

Referenzen