|
Download README.md from nopesadly/flash-attn-wheels: direct link, hf CLI and curl.
- Browser
- Download file 464 Bytes
-
https://huggingface.co/nopesadly/flash-attn-wheels/resolve/main/README.md
- Command line
-
hf download hf://nopesadly/flash-attn-wheels/README.md
-
curl -L -o README.md https://huggingface.co/nopesadly/flash-attn-wheels/resolve/main/README.md
464 Bytes
Flash-Attention Wheels for T4 GPU
Pre-compiled .whl files for NVIDIA T4 (sm_75).
| File | Python | PyTorch | CUDA |
|---|---|---|---|
flash_attn-2.8.3-cp312-cp312-linux_x86_64.whl |
3.12 | 2.10.0+cu128 | 12.8 |
Install
pip install "https://huggingface.co/nopesadly/flash-attn-wheels/resolve/main/flash_attn-2.8.3-cp312-cp312-linux_x86_64.whl"
Compiled with
TORCH_CUDA_ARCH_LIST=7.5— only compatible with T4 GPUs.