CVE-2026-105753
đļ mediumSummary
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 "Expecte
Description
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.
đ Relative Risk Intelligence
This CVE is Lower Risk - more severe than 46.5% of all 365,616 vulnerabilities in our database.
đ¯ CISA SSVC Assessment Updated: Oct 6, 2026
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H