vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-20"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/116xxx/CVE-2026-116178.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "0.20.0"
},
{
"fixed": "0.30.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.20.0"
},
{
"fixed": "0.30.0"
}
],
"source": "CPE_RANGE"
}
]
}