vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-129"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/93xxx/CVE-2026-93840.json"
}