README: add ISK 0.3.0 + sageattention mirror, list the wheels that were missing

README.md

@@ -17,8 +17,13 @@ Prebuilt Python 3.11 wheels.
 | 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-0.3.0-cp311-cp311-win_amd64.whl` | Windows x64 | 12.8 | 2.8 | built by us | FP8 dense + grouped GEMM, NVFP4 W4A4, INT8 W8A8 + ConvRot, fused QK-norm+RoPE. SM89 + SM120 |
 | `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 |
 | `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 |
@@ -29,17 +34,44 @@ Prebuilt Python 3.11 wheels.
 BASE=https://huggingface.co/deAPI-ai/image-server-wheels/resolve/main
 
 # Windows
+pip install $BASE/image_server_kernels-0.3.0-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/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 --no-deps $BASE/flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl
 ```
 
+`sageattention` is required by the MiniMax-H3 video model, which imports it
+unconditionally. Every other model that can use it falls back to SDPA when it is
+absent, so on a box that does not serve H3 the wheel is optional.
+
+> Wheels are Windows-only unless a `linux_x86_64` row exists above. There is
+> currently no Linux build of `image_server_kernels` or `sageattention` here.
+
 ## 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.
+`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.
+
+`sageattention` is **a mirror, not our build**. The library is
+[thu-ml/SageAttention](https://github.com/thu-ml/SageAttention) (Apache-2.0); the
+Windows 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`, `block_sparse_attn`, `q8_kernels`) were built in-house.
+The remaining wheels (`ace_step`, `qwen_tts`, `image_server_kernels`,
+`block_sparse_attn`, `q8_kernels`) were built in-house.