forked from Karylab-cklius/vllm
Harry MellorandGitHub
a1fe24d961
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
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``
|