xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 04:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: update fastsafetensors usage instructions (#22891)

Browse Source 
Signed-off-by: Nir Levy <bhr166@gmail.com>
This commit is contained in:
Nir 2025-08-14 22:56:54 +03:00 committed by GitHub
parent 33c63e9547
commit 637093ae26
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docs/models/extensions/fastsafetensor.md
View File

@ -2,4 +2,5 @@ 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. 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``
To enable this feature, use the ``--load-format fastsafetensors`` command-line argument