CVE-2025-24357

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.

Weakness classification

• security-advisories@github.com: CWE-502

Primary references

• security-advisories@github.com — Patch
• security-advisories@github.com — Issue Tracking, Patch
• security-advisories@github.com — Vendor Advisory
• security-advisories@github.com — Technical Description