CVE-2025-10164: lmsys sglang update_weights_from_tensor main deserialization

Published Sep 9, 2025
·
Updated

A security flaw has been discovered in lmsys sglang 0.4.6. Affected by this vulnerability is the function main of the file /updateweightsfromtensor. The manipulation of the argument serializednamedtensors results in deserialization. The attack can be launched remotely. The exploit has been released to the public and may be exploited. The vendor was contacted early about this disclosure but did not respond in any way.

Affected Software

1 affected component
Lmsys Sglang=0.4.6

Event History

Sep 9, 2025
CVE Published
via MITRE·06:32 PM
Data Sourced
via MITRE·06:32 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·07:15 PM
DescriptionSeverityWeakness

Frequently Asked Questions

1

What is the severity of CVE-2025-10164?

CVE-2025-10164 has been identified as a significant security vulnerability due to its ability to be exploited remotely via deserialization.

2

How do I fix CVE-2025-10164?

To mitigate CVE-2025-10164, upgrade lmsys sglang to version 0.4.7 or later, where the vulnerability is addressed.

3

What components of lmsys sglang are affected by CVE-2025-10164?

CVE-2025-10164 specifically affects the main function within the /update_weights_from_tensor file of lmsys sglang 0.4.6.

4

Can CVE-2025-10164 be exploited remotely?

Yes, CVE-2025-10164 allows for remote exploitation due to deserialization of manipulated arguments.

5

What are the potential risks associated with CVE-2025-10164?

The risks associated with CVE-2025-10164 include unauthorized access, data manipulation, and potential denial of service.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203