vllm
Affected
- introduced
0, fixed0.7.0(ecosystem)
Fixed versions
0.7.0
Fix
- Fixed version
0.7.0pip install --upgrade vllm==0.7.0
Advisory
Also known as: CVE-2025-24357, GHSA-rh4j-5rhw-hr54
The record has no summary.
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.
High Basis: CVSS v3 score 8.8, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
0, fixed 0.7.0 (ecosystem)0.7.0
0.7.0pip install --upgrade vllm==0.7.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0