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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-617"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105753.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.28.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "396204230423b7cc6798300926b8fa30190d26a9"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.28.0",
"range": [
{
"fixed": "2cf0a6915ce544dc493a0990f2ea38d81601128a"
}
],
"source": "REFERENCES_TAG"
}
]
}