vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-20",
"CWE-248",
"CWE-755"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105757.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.30.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "c55e15a44ec4127832d4a86928a356fdd9e68dbd"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.30.0",
"range": [
{
"fixed": "9ed533eb4adfe48aef7e569a08daeccd2a773fed"
}
],
"source": "REFERENCES_TAG"
}
]
}