- 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.
- Source
- security-advisories@github.com
- NVD status
- Received
CVSS 3.1
- Type
- Secondary
- Base score
- 7.5
- Impact score
- 5.9
- Exploitability score
- 1.6
- Vector string
- CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
- Severity
- HIGH
- security-advisories@github.com
- CWE-502
- Hype score
- Not currently trending