---
license: other
tags:
  - wheels
  - cuda
  - pytorch
  - windows
  - linux
---

# image-server-wheels

Prebuilt Python 3.11 wheels.

## Contents

| File | OS | CUDA | Torch | Source | Notes |
|---|---|---|---|---|---|
| `ace_step-1.6.0-py3-none-any.whl` | any | — | — | built by us | Pure-Python, cross-platform |
| `qwen_tts-0.1.1+deapi3-py3-none-any.whl` | any | — | — | built by us | Pure-Python, patched fork (`+deapi3`) |
| `image_server_kernels-0.4.3+cu128torch2.8-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | **Current.** FP8 dense + grouped GEMM, NVFP4 W4A4, INT8 W8A8 + ConvRot, W4A8, GGUF, fused QK-norm+RoPE, Sol-Attn. SM89 + SM120 |
| `image_server_kernels-0.4.3+cu129torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.9 | 2.8 | built by us | **Current.** Same op set |
| `image_server_kernels-0.4.2+cu128torch2.8-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | Previous build, kept as a rollback |
| `image_server_kernels-0.4.2+cu129torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.9 | 2.8 | built by us | Previous build, kept as a rollback |
| `image_server_kernels-0.3.0-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | Legacy. No Sol-Attn, no W4A8, no bundled GGUF kernels |
| `image_server_kernels-0.3.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.9 | 2.8 | built by us | Legacy. Same omissions as the Windows 0.3.0 |
| `block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | Used by video pipeline |
| `block_sparse_attn-0.0.2-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.8 | 2.8 | built by us | Used by video pipeline |
| `q8_kernels-0.0.5-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | Used by LTX video |
| `q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.8 | 2.8 | built by us | Used by LTX video |
| `sageattention-2.2.0+cu128torch2.8.0-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | [woct0rdho/SageAttention](https://github.com/woct0rdho/SageAttention/releases/tag/v2.2.0-windows) | Mirror of upstream release |
| `sageattention-2.2.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.9 | 2.8 | — | |
| `causal_conv1d-1.7.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.9 | 2.8 | built by us | Fused causal conv1d for Gated DeltaNet models. Built from unmodified upstream v1.7.0 source. No Windows build |
| `flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | [mjun0812/flash-attention-prebuild-wheels](https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/tag/v0.4.10) | Mirror of upstream release |
| `flash_attn-2.8.3+cu130torch2.10-cp311-cp311-win_amd64.whl` | Windows x64 | 13.0 | 2.10 | [mjun0812/flash-attention-prebuild-wheels](https://github.com/mjun0812/flash-attention-prebuild-wheels) | Mirror of upstream release |
| `flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl` | Linux x86_64 | 12.8 | 2.8 | [mjun0812/flash-attention-prebuild-wheels](https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/tag/v0.7.16) | Mirror of upstream release |

## Direct install

```bash
BASE=https://huggingface.co/deAPI-ai/image-server-wheels/resolve/main

# Windows
pip install $BASE/image_server_kernels-0.4.3+cu128torch2.8-cp311-cp311-win_amd64.whl
pip install $BASE/q8_kernels-0.0.5-cp311-cp311-win_amd64.whl
pip install $BASE/block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl
pip install $BASE/flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl
pip install $BASE/sageattention-2.2.0+cu128torch2.8.0-cp311-cp311-win_amd64.whl
pip install --no-deps $BASE/ace_step-1.6.0-py3-none-any.whl
pip install --no-deps $BASE/qwen_tts-0.1.1+deapi3-py3-none-any.whl

# Linux
pip install $BASE/image_server_kernels-0.4.3+cu129torch2.8-cp311-cp311-linux_x86_64.whl
pip install $BASE/q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl
pip install $BASE/block_sparse_attn-0.0.2-cp311-cp311-linux_x86_64.whl
pip install $BASE/sageattention-2.2.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl
pip install --no-deps $BASE/causal_conv1d-1.7.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl
pip install --no-deps $BASE/flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl
```

Wheels are built for **Python 3.11** and the CUDA/torch pair named in each filename.
Installing one against a different torch build is the first thing to suspect if the
import fails.

## Credits

`flash_attn` wheels are mirrored from
[mjun0812/flash-attention-prebuild-wheels](https://github.com/mjun0812/flash-attention-prebuild-wheels)
— all credit for those builds goes to the upstream author.

The Windows `sageattention` wheel is **a mirror, not our build**. The library is
[thu-ml/SageAttention](https://github.com/thu-ml/SageAttention) (Apache-2.0); the wheel
is built and published by
[woct0rdho](https://github.com/woct0rdho/SageAttention/releases), and we found it
through [wildminder/AI-windows-whl](https://github.com/wildminder/AI-windows-whl),
which indexes Windows CUDA wheels. All credit for the library and the build goes to
them. The file here is byte-identical to the upstream release
(`sha256:4379951403809dfcd5b1e10d35e287abf42afafb7b27615c09d6062cfbdf230a`).

We mirror third-party wheels so the install scripts have a single source of truth and
do not break if upstream release URLs change.

The remaining wheels (`ace_step`, `qwen_tts`, `image_server_kernels`,
`block_sparse_attn`, `q8_kernels`) were built in-house.

The Linux `causal_conv1d` wheel is built in-house from the unmodified source of
[Dao-AILab/causal-conv1d](https://github.com/Dao-AILab/causal-conv1d/tree/v1.7.0) v1.7.0
(BSD-3-Clause, copyright the causal-conv1d contributors). Its `LICENSE` and `AUTHORS`
ship inside the wheel under `dist-info/licenses/`. All credit for the library goes to
its authors.