vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-190"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73558.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.27.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "451227cb3ff07989698fed982c2d3e4300257924"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.27.0",
"range": [
{
"fixed": "4bdc8a788d2e2ce9165d552b3d4d8b72604626bf"
}
],
"source": "REFERENCES_TAG"
}
]
}