vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-129"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/93xxx/CVE-2026-93841.json"
}{
"extracted_events": [
{
"introduced": "0"
},
{
"last_affected": "0.29.0"
},
{
"fixed": "0.29.0"
}
],
"source": [
"AFFECTED_FIELD",
"DESCRIPTION"
]
}