sparsevideo 0.1.0__tar.gz

sparsevideo-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Jiayi Luo, Beihang University & Zhongguanchun Academy
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

sparsevideo-0.1.0/NOTICE

@@ -0,0 +1,23 @@
+SparseVideo
+Copyright 2026 Jiayi Luo, Beihang University & Zhongguanchun Academy
+
+Licensed under the Apache License, Version 2.0 (the "License"); see the LICENSE
+file for the full terms.
+
+This product bundles and/or builds upon the third-party software components
+listed below, each under its own license. The full license texts are retained
+alongside the corresponding sources within this distribution.
+
+  - FlashInfer (Apache-2.0) — github.com/flashinfer-ai/flashinfer
+      src/sparsevideo/kernels/_flashinfer/  (incl. derived flashomni runtime)
+  - spdlog (MIT, (c) 2016 Gabi Melman) — github.com/gabime/spdlog
+      src/sparsevideo/kernels/_flashinfer/spdlog/
+  - SpargeAttn (Apache-2.0) — github.com/thu-ml/SpargeAttn
+      src/sparsevideo/kernels/native/spargeattn/
+  - SageAttention (Apache-2.0) — github.com/thu-ml/SageAttention
+      src/sparsevideo/kernels/native/sageattention/
+  - Block-Sparse-Attention (BSD-3-Clause) — github.com/mit-han-lab/Block-Sparse-Attention
+      src/sparsevideo/kernels/native/draft_block_sparse/
+
+NVIDIA CUTLASS (BSD-3-Clause) is a build-time-only dependency: it is not shipped
+in this package and is fetched at the pinned ref by kernels/_cutlass.py.

sparsevideo-0.1.0/PKG-INFO

@@ -0,0 +1,129 @@
+Metadata-Version: 2.4
+Name: sparsevideo
+Version: 0.1.0
+Summary: Plug-and-play sparse attention for video diffusion models
+Author: Jiayi Luo
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/Mutual-Luo/SparseVideo
+Keywords: sparse-attention,video-diffusion,inference,triton,cuda
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: torch>=2.1.0
+Requires-Dist: diffusers>=0.30.0
+Requires-Dist: einops>=0.6.0
+Requires-Dist: pyyaml>=5.4
+Requires-Dist: jinja2>=3.0
+Requires-Dist: filelock>=3.0
+Requires-Dist: packaging>=21.0
+Requires-Dist: triton>=2.2.0
+Requires-Dist: diffsynth>=2.0.12
+Provides-Extra: flashinfer
+Requires-Dist: flashinfer-python>=0.1.0; extra == "flashinfer"
+Provides-Extra: all
+Requires-Dist: flashinfer-python>=0.1.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: ruff>=0.4.0; extra == "dev"
+Dynamic: license-file
+
+<p align="center">
+  <img src="assets/logo.png" alt="SparseVideo Logo" width="260"/>
+</p>
+
+<!-- <h1 align="center">SparseVideo</h1> -->
+
+<p align="center">A one-line, plug-and-play sparse attention framework for accelerating video diffusion inference.</p>
+
+
+## 📦 Installation
+
+**From PyPI**
+
+```bash
+pip install sparsevideo --no-build-isolation
+```
+
+**From source**
+
+```bash
+git clone https://github.com/Mutual-Luo/SparseVideo.git
+cd SparseVideo
+MAX_JOBS=8 pip install -e . --no-build-isolation
+```
+
+## 🚀 Quick Start
+
+```diff
+  import torch
+  from diffusers import WanPipeline
+  import sparsevideo
+
+  pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", torch_dtype=torch.bfloat16)
+  pipe.to("cuda")
+
++ pipe = sparsevideo.replace_attention(pipe, method="svoo")
+
+  video = pipe("A cat playing piano", num_frames=81, num_inference_steps=50).frames[0]
+```
+
+## ⚡ Supported Sparse Attention Methods
+
+| | Method | | Method | | Method |
+|:---:|---|:---:|---|:---:|---|
+| ✅ | `Dense` (baseline) | ✅ | `SpargeAttn` [[paper]](https://arxiv.org/abs/2502.18137) | ✅ | `Adacluster` [[paper]](https://arxiv.org/abs/2604.18348) |
+| ✅ | `SVG1` [[paper]](https://arxiv.org/abs/2502.01776) | ✅ | `Radial` [[paper]](https://arxiv.org/abs/2506.19852) | ✅ | `SVOO` [[paper]](https://arxiv.org/abs/2603.18636) |
+| ✅ | `SVG2` [[paper]](https://arxiv.org/abs/2505.18875) | ✅ | `STA` [[paper]](https://arxiv.org/abs/2502.04507) | ✅ | `FlashOmni` [[paper]](https://arxiv.org/abs/2509.25401) |
+| ✅ | `SVG-EAR` [[paper]](https://arxiv.org/abs/2603.08982) | ✅ | `DraftAttention` [[paper]](https://arxiv.org/abs/2505.14708) | | |
+
+## 🧩 Supported Frameworks
+
+Works as a drop-in, one-line replacement for both **Diffusers** and **DiffSynth-Studio** pipelines. Just call `sparsevideo.replace_attention(pipe, method=...)`, no model modifications required.
+
+### Diffusers
+
+Supported 34 models:
+
+| | Model | | Model | | Model |
+|:---:|---|:---:|---|:---:|---|
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text-to-Video A14B</sub> | <sub>✅</sub> | <sub>Video-as-Prompt Wan 2.1 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Image-to-Video A14B</sub> | <sub>✅</sub> | <sub>HunyuanVideo Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Speech-to-Video 14B</sub> | <sub>✅</sub> | <sub>HunyuanVideo Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 VACE 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Animate 14B</sub> | <sub>✅</sub> | <sub>CogVideoX Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 VACE 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control</sub> | <sub>✅</sub> | <sub>CogVideoX Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control-Camera</sub> | <sub>✅</sub> | <sub>EasyAnimate V5 Text-to-Video 12B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B InP</sub> | <sub>✅</sub> | <sub>SkyReels-V2 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-Video Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control</sub> | <sub>✅</sub> | <sub>SkyReels-V2 Image-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-Video Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control-Camera</sub> | <sub>✅</sub> | <sub>MoVA 720P</sub> | <sub>✅</sub> | <sub>LTX-2</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control</sub> | <sub>✅</sub> | <sub>LongCat-Video</sub> | <sub>✅</sub> | <sub>Mochi-1</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control-Camera</sub> | <sub>✅</sub> | <sub>Krea Realtime Video 14B</sub> | <sub>✅</sub> | <sub>Allegro</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Speed-Control 1.3B</sub> | | | | |
+
+### DiffSynth-Studio
+
+Supported 30 models:
+
+| | Model | | Model | | Model |
+|:---:|---|:---:|---|:---:|---|
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Animate 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control-Camera</sub> | <sub>✅</sub> | <sub>Wan 2.2 Dancer 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B 480P</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B 720P</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control-Camera</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control-Camera</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 First-Last-Frame-to-Video 14B 720P</sub> | <sub>✅</sub> | <sub>Wan 2.1 VACE 1.3B</sub> | <sub>✅</sub> | <sub>LongCat-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Speed-Control 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.1 VACE 14B</sub> | <sub>✅</sub> | <sub>Video-as-Prompt Wan 2.1 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text-to-Video A14B</sub> | <sub>✅</sub> | <sub>Krea Realtime Video 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B InP</sub> | <sub>✅</sub> | <sub>Wan 2.2 Image-to-Video A14B</sub> | <sub>✅</sub> | <sub>MoVA 720P</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 14B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text/Image-to-Video 5B</sub> | <sub>✅</sub> | <sub>LTX-2</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 14B InP</sub> | <sub>✅</sub> | <sub>Wan 2.2 Speech-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-2.3</sub> |
+
+## 📄 License
+
+Apache-2.0

sparsevideo-0.1.0/README.md

@@ -0,0 +1,92 @@
+<p align="center">
+  <img src="assets/logo.png" alt="SparseVideo Logo" width="260"/>
+</p>
+
+<!-- <h1 align="center">SparseVideo</h1> -->
+
+<p align="center">A one-line, plug-and-play sparse attention framework for accelerating video diffusion inference.</p>
+
+
+## 📦 Installation
+
+**From PyPI**
+
+```bash
+pip install sparsevideo --no-build-isolation
+```
+
+**From source**
+
+```bash
+git clone https://github.com/Mutual-Luo/SparseVideo.git
+cd SparseVideo
+MAX_JOBS=8 pip install -e . --no-build-isolation
+```
+
+## 🚀 Quick Start
+
+```diff
+  import torch
+  from diffusers import WanPipeline
+  import sparsevideo
+
+  pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", torch_dtype=torch.bfloat16)
+  pipe.to("cuda")
+
++ pipe = sparsevideo.replace_attention(pipe, method="svoo")
+
+  video = pipe("A cat playing piano", num_frames=81, num_inference_steps=50).frames[0]
+```
+
+## ⚡ Supported Sparse Attention Methods
+
+| | Method | | Method | | Method |
+|:---:|---|:---:|---|:---:|---|
+| ✅ | `Dense` (baseline) | ✅ | `SpargeAttn` [[paper]](https://arxiv.org/abs/2502.18137) | ✅ | `Adacluster` [[paper]](https://arxiv.org/abs/2604.18348) |
+| ✅ | `SVG1` [[paper]](https://arxiv.org/abs/2502.01776) | ✅ | `Radial` [[paper]](https://arxiv.org/abs/2506.19852) | ✅ | `SVOO` [[paper]](https://arxiv.org/abs/2603.18636) |
+| ✅ | `SVG2` [[paper]](https://arxiv.org/abs/2505.18875) | ✅ | `STA` [[paper]](https://arxiv.org/abs/2502.04507) | ✅ | `FlashOmni` [[paper]](https://arxiv.org/abs/2509.25401) |
+| ✅ | `SVG-EAR` [[paper]](https://arxiv.org/abs/2603.08982) | ✅ | `DraftAttention` [[paper]](https://arxiv.org/abs/2505.14708) | | |
+
+## 🧩 Supported Frameworks
+
+Works as a drop-in, one-line replacement for both **Diffusers** and **DiffSynth-Studio** pipelines. Just call `sparsevideo.replace_attention(pipe, method=...)`, no model modifications required.
+
+### Diffusers
+
+Supported 34 models:
+
+| | Model | | Model | | Model |
+|:---:|---|:---:|---|:---:|---|
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text-to-Video A14B</sub> | <sub>✅</sub> | <sub>Video-as-Prompt Wan 2.1 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Image-to-Video A14B</sub> | <sub>✅</sub> | <sub>HunyuanVideo Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Speech-to-Video 14B</sub> | <sub>✅</sub> | <sub>HunyuanVideo Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 VACE 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.2 Animate 14B</sub> | <sub>✅</sub> | <sub>CogVideoX Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 VACE 14B</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control</sub> | <sub>✅</sub> | <sub>CogVideoX Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control-Camera</sub> | <sub>✅</sub> | <sub>EasyAnimate V5 Text-to-Video 12B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B InP</sub> | <sub>✅</sub> | <sub>SkyReels-V2 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-Video Text-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control</sub> | <sub>✅</sub> | <sub>SkyReels-V2 Image-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-Video Image-to-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control-Camera</sub> | <sub>✅</sub> | <sub>MoVA 720P</sub> | <sub>✅</sub> | <sub>LTX-2</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control</sub> | <sub>✅</sub> | <sub>LongCat-Video</sub> | <sub>✅</sub> | <sub>Mochi-1</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control-Camera</sub> | <sub>✅</sub> | <sub>Krea Realtime Video 14B</sub> | <sub>✅</sub> | <sub>Allegro</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Speed-Control 1.3B</sub> | | | | |
+
+### DiffSynth-Studio
+
+Supported 30 models:
+
+| | Model | | Model | | Model |
+|:---:|---|:---:|---|:---:|---|
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Animate 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Text-to-Video 14B</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 1.3B Control-Camera</sub> | <sub>✅</sub> | <sub>Wan 2.2 Dancer 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B 480P</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Image-to-Video 14B 720P</sub> | <sub>✅</sub> | <sub>Wan 2.1-Fun V1.1 14B Control-Camera</sub> | <sub>✅</sub> | <sub>Wan 2.2-Fun A14B Control-Camera</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 First-Last-Frame-to-Video 14B 720P</sub> | <sub>✅</sub> | <sub>Wan 2.1 VACE 1.3B</sub> | <sub>✅</sub> | <sub>LongCat-Video</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1 Speed-Control 1.3B</sub> | <sub>✅</sub> | <sub>Wan 2.1 VACE 14B</sub> | <sub>✅</sub> | <sub>Video-as-Prompt Wan 2.1 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text-to-Video A14B</sub> | <sub>✅</sub> | <sub>Krea Realtime Video 14B</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 1.3B InP</sub> | <sub>✅</sub> | <sub>Wan 2.2 Image-to-Video A14B</sub> | <sub>✅</sub> | <sub>MoVA 720P</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 14B Control</sub> | <sub>✅</sub> | <sub>Wan 2.2 Text/Image-to-Video 5B</sub> | <sub>✅</sub> | <sub>LTX-2</sub> |
+| <sub>✅</sub> | <sub>Wan 2.1-Fun 14B InP</sub> | <sub>✅</sub> | <sub>Wan 2.2 Speech-to-Video 14B</sub> | <sub>✅</sub> | <sub>LTX-2.3</sub> |
+
+## 📄 License
+
+Apache-2.0

sparsevideo-0.1.0/pyproject.toml

@@ -0,0 +1,66 @@
+[build-system]
+requires = ["setuptools>=77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sparsevideo"
+version = "0.1.0"
+description = "Plug-and-play sparse attention for video diffusion models"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE"]
+readme = "README.md"
+keywords = ["sparse-attention", "video-diffusion", "inference", "triton", "cuda"]
+authors = [
+    { name = "Jiayi Luo" },
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+# Everything needed to run is declared here so that, with torch already present
+# (required to compile the kernels, exactly like flash-attn), a single
+#   pip install sparsevideo --no-build-isolation
+# pulls in every runtime dependency automatically — no piecemeal setup.
+dependencies = [
+    "torch>=2.1.0",
+    "diffusers>=0.30.0",
+    "einops>=0.6.0",
+    "pyyaml>=5.4",
+    "jinja2>=3.0",
+    "filelock>=3.0",
+    "packaging>=21.0",
+    "triton>=2.2.0",
+    "diffsynth>=2.0.12",
+]
+
+[project.optional-dependencies]
+# flashinfer-python is the only heavy, torch/CUDA-version-coupled backend, kept
+# optional so a version mismatch can never break the base install. Needed only
+# for the `flashomni` method:  pip install sparsevideo[flashinfer]
+flashinfer = ["flashinfer-python>=0.1.0"]
+all = ["flashinfer-python>=0.1.0"]
+dev = ["pytest>=7.0", "ruff>=0.4.0"]
+
+[project.urls]
+Repository = "https://github.com/Mutual-Luo/SparseVideo"
+
+[project.scripts]
+sparsevideo-build-kernels = "sparsevideo.kernels._build:main"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I"]
+ignore = ["E501"]

sparsevideo-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+