mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-14 00:45:36 +08:00
d6195a748b
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.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``
|