CVE-2025-24357 Details
Description
vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.
A vulnerability in the vLLM library, specifically in the model weight loading functionality, allows for arbitrary code execution. This issue arises because the library uses the torch.load function to deserialize model weights from Hugging Face, with the default setting of weights_only parameter allowing potentially harmful code to execute during the unpickling process. The vulnerability affects vLLM versions through 0.7.0 and has been addressed in version 0.7.0.
Users can update to vLLM version 0.7.0 or later, where this vulnerability has been fixed.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Jan 27, 2025References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-502 | Deserialization of Untrusted Data | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | < 0.7.0 |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| Jun 27, 2025 | Initial Analysis | [email protected] |
| Jan 27, 2025 | New CVE Received | [email protected] |