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.
History

Thu, 13 Aug 2026 18:30:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Thu, 13 Aug 2026 15:15:00 +0000

Type Values Removed Values Added
Description 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.
Title vLLM: Cross-User Data Leak Vulnerability
Weaknesses CWE-190
References
Metrics cvssV3_1

{'score': 5.3, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-08-13T15:38:40.181Z

Reserved: 2026-08-12T20:53:46.380Z

Link: CVE-2026-73558

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-13T15:20:18.220

Modified: 2026-08-13T16:19:05.760

Link: CVE-2026-73558

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-13T18:15:04Z