A AegiFlow
MEDIUMCVSS 5.3EPSS 0.3%

CVE-2026-73558

CVE-2026-73558 updated by NVD

Published
2026-09-08
Modified
2026-09-11
EPSS percentile
18%
Sources
github-advisory, nvd

Summary

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 packages

EcosystemPackageAffected versionsFixed versions
PyPIvllm0.27.0

Remediation: Upgrade to 0.27.0 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

Includes data from the National Vulnerability Database (NIST). NVD data is in the public domain; this page is not endorsed by NIST.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.