Instructions to use flashrt/fp8-kv-attention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use flashrt/fp8-kv-attention with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("flashrt/fp8-kv-attention", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Promote latest kernel artifacts to main
Verified signaturedd7e74f -
Promote latest kernel artifacts to main
Verified signature63ffb0f
-
Promote latest kernel artifacts to main
Verified signature8e1d702 -
Promote latest kernel artifacts to main
Verified signature19dc74e
-
Promote latest kernel artifacts to main
Verified signaturebd9c69a