mirror of https://github.com/vllm-project/vllm.git
6 lines
418 B
Markdown
6 lines
418 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.
|
|
For enabling this feature, set the environment variable ``USE_FASTSAFETENSOR`` to ``true``
|