vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-639"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105755.json",
"unresolved_ranges": [
{
"extracted_events": [
{
"range": [
{
"fixed": "030.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StringRangeExpression"
}
]
}
]
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.30.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "ee17d0d869203ef9a35ad73358a4987bba14b1fc"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.30.0",
"range": [
{
"fixed": "9ed533eb4adfe48aef7e569a08daeccd2a773fed"
}
],
"source": "REFERENCES_TAG"
}
]
}