CVE-2026-73558: Vllm

Medium severity, CVSS 5.3. EPSS: 0.4% chance of exploitation in the next 30 days.

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.

Affected products

• Vllm Vllm: before 0.27.0 (fixed in 0.27.0)

Published 2026-08-13. Last modified 2026-09-28.