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.
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
| Link | Tags |
|---|---|
| https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 | vendor advisory |
| https://github.com/vllm-project/vllm/pull/12366 | issue tracking patch |
| https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04 | patch |
| https://pytorch.org/docs/stable/generated/torch.load.html | technical description |