Precompiled Wheels for Experimental Environments (CUDA 13.0)

Dedykowane, prekompilowane pliki flash attention 2 (.whl) .

Flash Attention 2 (v2.8.3)
- CUDA: 13.0
- PyTorch: 2.12.x
- Python: 3.12 (Linux x86_64)

Instalation

python3 -m pip install "https://huggingface.co/datasets/HattoriHanzo1/flash-attn2/resolve/main/flash_attn-2.8.3+cu130torch2.12-cp312-cp312-linux_x86_64.whl" --no-build-isolation

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support