---
language:
- en
---

| Prebuilt Wheels                                | Python Versions | PyTorch Versions | CUDA Versions  | Source                                                                    |
|------------------------------------------------|-----------------|------------------|----------------|---------------------------------------------------------------------------|
| [Flash-Attention 2.7.4.post1](https://huggingface.co/lym00/win_amd64_prebuilt_wheels/blob/main/flash_attn-2.7.4.post1-cp312-cp312-win_amd64.whl)                   | 3.12            | 2.8.0.dev        | 12.8.1         | [Dao-AILab/flash-attention](https://github.com/Dao-AILab/flash-attention) |
| [SageAttention2.2.0](https://huggingface.co/lym00/win_amd64_prebuilt_wheels/blob/main/sageattention-2.2.0-cp312-cp312-win_amd64.whl)                               | 3.12            | 2.9.0.dev        | 12.9.1         | [thu-ml/SageAttention](https://github.com/thu-ml/SageAttention) or [jt-zhang/SageAttention2_plus](https://huggingface.co/jt-zhang/SageAttention2_plus) |
| SageAttention3 (pending approval)             | 3.12            | 2.9.0.dev        | 12.9.1         | [jt-zhang/SageAttention3](https://huggingface.co/jt-zhang/SageAttention3) |
| Flash-Attention_2.8.1       | 3.12            | 2.9.0.dev        | 12.9.1         | [Dao-AILab/flash-attention](https://github.com/Dao-AILab/flash-attention)  |
| xformers_0.0.31.post1       | 3.12            | 2.9.0.dev        | 12.9.1         | [facebookresearch/xformers](https://github.com/facebookresearch/xformers) |
| INSERT                                         | INSERT          | INSERT           | INSERT         | INSERT |