Files
vllm/docs/models/extensions/fastsafetensor.md
2025-08-14 19:56:54 +00:00

7 lines
416 B
Markdown

Loading Model weights with fastsafetensors
===================================================================
Using fastsafetensors library enables loading model weights to GPU memory by leveraging GPU direct storage. See [their GitHub repository](https://github.com/foundation-model-stack/fastsafetensors) for more details.
To enable this feature, use the ``--load-format fastsafetensors`` command-line argument