Initial upload of prebuilt wheels

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ace_step-1.6.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl filter=lfs diff=lfs merge=lfs -text
+flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl filter=lfs diff=lfs merge=lfs -text
+flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+flash_attn-2.8.3+cu130torch2.10-cp311-cp311-win_amd64.whl filter=lfs diff=lfs merge=lfs -text
+q8_kernels-0.0.5-cp311-cp311-win_amd64.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,50 @@
+---
+license: other
+tags:
+  - wheels
+  - cuda
+  - pytorch
+  - windows
+  - linux
+---
+
+# image-server-wheels
+
+Prebuilt Python wheels used by the [image-server](https://github.com/) install scripts
+(`install.ps1` on Windows, `install.sh` on Linux). Hosted here because some wheels
+exceed GitHub's 100 MB per-file limit.
+
+All wheels target **Python 3.11**. The install scripts fall back to this repo
+automatically when the wheel is not found locally in `scripts/publish/whl/`.
+
+## Contents
+
+| File | OS | CUDA | Torch | Source | Notes |
+|---|---|---|---|---|---|
+| `ace_step-1.6.0-py3-none-any.whl` | any | — | — | built by us | Pure-Python, cross-platform |
+| `block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl` | Windows x64 | 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 |
+| `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/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 --no-deps $BASE/ace_step-1.6.0-py3-none-any.whl
+
+# Linux
+pip install --no-deps $BASE/flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl
+```
+
+## 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. We mirror them here so the install scripts have a single source of truth and do not break if upstream release URLs change.
+
+The remaining wheels (`ace_step`, `block_sparse_attn`, `q8_kernels`) were built in-house.

ace_step-1.6.0-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b08dc35287e4bb6b519bedbb8de6f184bd283cd4c26713c5d9d732eb6c14ef
+size 2477912

block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5518b9a92c53ff7540b0a091f2d35e4cf717fef4aec319599328856e0f0f3408
+size 181538163

flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9b1b901ea3b60c10dac362a86d490d6385bdce0714b1be7311df7708c5e16f
+size 250764791

flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3139fa0a11a517057336890376a00ae55ab6e87278c02a68387c24626e597bd9
+size 253476553

flash_attn-2.8.3+cu130torch2.10-cp311-cp311-win_amd64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fb6b6981d601b0c8d2f33ba2d4c69b8954490cbc152b9d8cdc2b6f9616f5a2
+size 239527638

q8_kernels-0.0.5-cp311-cp311-win_amd64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95401ac0874c6b924ee0a6e6a7b3aa2cbfff260bd47ea4f0e0d92f887ae29f81
+size 24962066