fp8

2025-12-31 00:19:52 +00:00
329 changed files with 3934 additions and 43125 deletions
@@ -61,7 +61,7 @@ steps:
                - "pyproject.toml"
                - "docker/Dockerfile.python3.12"
              config:
-                command: "timeout 90m .buildkite/scripts/pr_test.sh"
+                command: "timeout 45m .buildkite/scripts/pr_test.sh"
                label: "SSIM Tests"
                env:
                  - TEST_TYPE=ssim
@@ -76,7 +76,7 @@ steps:
                - "pyproject.toml"
                - "docker/Dockerfile.python3.12"
              config:
-                command: "timeout 20m .buildkite/scripts/pr_test.sh"
+                command: "timeout 15m .buildkite/scripts/pr_test.sh"
                label: "LoRA Inference Tests"
                env:
                  - TEST_TYPE=inference_lora
@@ -156,23 +156,8 @@ jobs:
          
          # Fix the wheel to be manylinux compliant
          pip install auditwheel
-          # Point auditwheel at torch libs, but do not vendor them into the wheel.
-          TORCH_LIB_DIR=$(python - <<'PY'
-          import os
-          import torch
-
-          print(os.path.join(os.path.dirname(torch.__file__), "lib"))
-          PY
-          )
-          export LD_LIBRARY_PATH="${TORCH_LIB_DIR}:${LD_LIBRARY_PATH}"
          # Target manylinux_2_35 (Ubuntu 22.04 native)
-          auditwheel repair dist/*.whl --plat manylinux_2_35_x86_64 -w fixed_dist \
-            --exclude libtorch_cuda.so \
-            --exclude libtorch_cpu.so \
-            --exclude libtorch.so \
-            --exclude libc10.so \
-            --exclude libc10_cuda.so \
-            --exclude libtorch_python.so
+          auditwheel repair dist/*.whl --plat manylinux_2_35_x86_64 -w fixed_dist
          # Move fixed wheels back to dist for upload consistency
          rm dist/*.whl
          mv fixed_dist/*.whl dist/
@@ -68,7 +68,7 @@ repos:
    entry: bash
    args:
      - -c
-      - 'git ls-files | grep -v "^\"*fastvideo/tests/ssim/" | grep -v "^\"*fastvideo/tests/inference/lora/L40S_reference_videos/" | grep " " && echo "Filenames should not contain spaces!" && exit 1 || exit 0'
+      - 'git ls-files | grep -v "^fastvideo/tests/ssim/" | grep -v "^fastvideo/tests/inference/lora/L40S_reference_videos/" | grep " " && echo "Filenames should not contain spaces!" && exit 1 || exit 0'
    language: system
    always_run: true
    pass_filenames: false
@@ -1,42 +0,0 @@
-# Repository Guidelines
-
-## Project Structure & Module Organization
- Core Python package: `fastvideo/` (models, pipelines, training, distributed runtime, CLI entrypoints).
- CUDA/custom kernels: `fastvideo-kernel/` (separate build/test flow).
- Tests:
-  - `fastvideo/tests/` for package-level tests (dataset, encoders, inference, training, SSIM, workflow).
-  - `tests/local_tests/` for additional local/component checks.
- Docs and guides: `docs/` (MkDocs source), with contributor docs in `docs/contributing/`.
- Runnable examples and scripts: `examples/` and `scripts/`.
- Static assets: `assets/`, `images/`, `videos/`, and `comfyui/assets/`.
-
-## Build, Test, and Development Commands
- `uv pip install -e .[dev]`: editable install with lint/test extras.
- `pre-commit install --hook-type pre-commit --hook-type commit-msg`: enable local hooks.
- `pre-commit run --all-files`: run formatter/lint/type/spelling checks.
- `pytest tests/`: run top-level test suite.
- `pytest fastvideo/tests/ -v`: run package tests.
- `pytest fastvideo/tests/ssim/ -vs`: run SSIM regression tests (GPU-heavy).
- `cd fastvideo-kernel && ./build.sh`: build kernel extensions.
-
-## Coding Style & Naming Conventions
- Python 3.10+; 4-space indentation; keep code and imports readable and explicit.
- Style tools are configured in `pyproject.toml` and `.pre-commit-config.yaml`:
-  - `yapf` (format), `ruff` (lint, auto-fix), `mypy` (typing), `codespell`.
- Target line length is 80.
- Naming: `snake_case` for functions/files, `PascalCase` for classes, `UPPER_SNAKE_CASE` for constants.
-
-## Testing Guidelines
- Use `pytest` and place tests near relevant domains (e.g., `fastvideo/tests/encoders/`).
- Prefer descriptive names like `test_<feature>_<expected_behavior>.py`.
- For new pipelines/backends, include at least one regression-oriented test; add SSIM coverage when output quality must be preserved.
- Document GPU assumptions in tests that require specific hardware.
-
-## Commit & Pull Request Guidelines
- Follow existing commit style: short subject with optional tag prefix, e.g. `[bugfix]: ...`, `[feat]: ...`, `[misc]: ...`, and include PR reference like `(#1234)` when applicable.
- Keep commits focused by concern (feature, refactor, fix).
- PRs should include:
-  - clear problem/solution summary,
-  - test evidence (`pytest`/SSIM outputs or rationale if skipped),
-  - linked issue/PR context,
-  - screenshots or sample outputs for UI/demo/docs changes.
@@ -1 +0,0 @@
-@AGENTS.md
@@ -1,49 +1,43 @@
 <div align="center">
 <img src=assets/logos/logo.svg width="30%"/>
 </div>
-
-<p align="center">
-     | <a href="https://hao-ai-lab.github.io/FastVideo"><b>Documentation</b></a> | <a href="https://hao-ai-lab.github.io/FastVideo/inference/inference_quick_start/"><b> Quick Start</b></a> | <a href="https://github.com/hao-ai-lab/FastVideo/discussions/982"  target="_blank"><b>Weekly Dev Meeting</b></a>  | 🟣💬 <a href="https://join.slack.com/t/fastvideo/shared_invite/zt-3f4lao1uq-u~Ipx6Lt4J27AlD2y~IdLQ" target="_blank"> <b>Slack</b> </a> |  🟣💬 <a href="https://ibb.co/sv3MMKyv" target="_blank"> <b> WeChat </b> </a> |
-</p>
-
 **FastVideo is a unified post-training and inference framework for accelerated video generation.**

+FastVideo features an end-to-end unified pipeline for accelerating diffusion models, starting from data preprocessing to model training, finetuning, distillation, and inference. FastVideo is designed to be modular and extensible, allowing users to easily add new optimizations and techniques. Whether it is training-free optimizations or post-training optimizations, FastVideo has you covered.
+
+<p align="center">
+    | 🕹️ <a href="https://fastwan.fastvideo.org/"<b>Online Demo</b></a> | <a href="https://hao-ai-lab.github.io/FastVideo"><b>Documentation</b></a> | <a href="https://hao-ai-lab.github.io/FastVideo/inference/inference_quick_start/"><b> Quick Start</b></a> | 🤗 <a href="https://huggingface.co/collections/FastVideo/fastwan-6886a305d9799c8cd1496408"  target="_blank"><b>FastWan</b></a>  | 🟣💬 <a href="https://join.slack.com/t/fastvideo/shared_invite/zt-3f4lao1uq-u~Ipx6Lt4J27AlD2y~IdLQ" target="_blank"> <b>Slack</b> </a> |  🟣💬 <a href="https://ibb.co/c7g1qdD" target="_blank"> <b> WeChat </b> </a> |
+</p>
+
+<div align="center">
+<img src=assets/fastwan.png width="90%"/>
+</div>
+
 ## NEWS
-
- `2025/11/19`: Release [CausalWan2.2 I2V A14B Preview](https://huggingface.co/FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers) models, [Blog](https://hao-ai-lab.github.io/blogs/fastvideo_causalwan_preview/) and [Inference Code!](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py)
- `2025/08/04`: Release [FastWan](https://hao-ai-lab.github.io/FastVideo/distillation/dmd) models and [Sparse-Distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/).
-
-### More News
-
- `2025/06/14`: Release finetuning and inference code for [VSA](https://arxiv.org/pdf/2505.13389)
- `2025/04/24`: [FastVideo V1](https://hao-ai-lab.github.io/blogs/fastvideo/) is released!
- `2025/02/18`: Release the inference code for [Sliding Tile Attention](https://hao-ai-lab.github.io/blogs/sta/).
+- ```2025/11/19```: Release [CausalWan2.2 I2V A14B Preview](https://huggingface.co/FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers) models, [Blog](https://hao-ai-lab.github.io/blogs/fastvideo_causalwan_preview/) and [Inference Code!](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py)
+- ```2025/08/04```: Release [FastWan](https://hao-ai-lab.github.io/FastVideo/distillation/dmd) models and [Sparse-Distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/).
+- ```2025/06/14```: Release finetuning and inference code for [VSA](https://arxiv.org/pdf/2505.13389)
+- ```2025/04/24```: [FastVideo V1](https://hao-ai-lab.github.io/blogs/fastvideo/) is released!
+- ```2025/02/18```: Release the inference code for [Sliding Tile Attention](https://hao-ai-lab.github.io/blogs/sta/).

 ## Key Features

 FastVideo has the following features:
-
- End-to-end post-training support for bidirectional and autoregressive models:
+- End-to-end post-training support:
+  - [Sparse distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/) for Wan2.1 and Wan2.2 to achineve >50x denoising speedup
+  - Data preprocessing pipeline for video data
  - Support full finetuning and LoRA finetuning for state-of-the-art open video DiTs
-  - Data preprocessing pipeline for video, image, and text data
-  - Distribution Matching Distillation (DMD2) stepwise distillation.
-  - Sparse attention with [Video Sparse Attention](https://arxiv.org/pdf/2505.13389)
-  - [Sparse distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/) to achieve >50x denoising speedup
-  - Scalable training with FSDP2, sequence parallelism, and selective activation checkpointing.
-  - Causal distillation through Self-Forcing
-  - See this [page](https://hao-ai-lab.github.io/FastVideo/training/overview/) for full list of supported models and recipes.
+  - Scalable training with FSDP2, sequence parallelism, and selective activation checkpointing, with near linear scaling to 64 GPUs
 - State-of-the-art performance optimizations for inference
-  - Sequence Parallelism for distributed inference
-  - Multiple state-of-the-art attention backends
-  - User-friendly CLI and Python API
-  - See this [page](https://hao-ai-lab.github.io/FastVideo/inference/optimizations/) for full list of supported optimizations.
+  - [Video Sparse Attention](https://arxiv.org/pdf/2505.13389)
+  - [Sliding Tile Attention](https://arxiv.org/pdf/2502.04507)
+  - [TeaCache](https://arxiv.org/pdf/2411.19108)
+  - [Sage Attention](https://arxiv.org/abs/2410.02367)
 - Diverse hardware and OS support
  - Support H100, A100, 4090
  - Support Linux, Windows, MacOS
-  - See this [page](https://hao-ai-lab.github.io/FastVideo/inference/hardware_support/) for full list of supported hardware and OS.

 ## Getting Started
-
 We recommend using an environment manager such as `Conda` to create a clean environment:

 ```bash
@@ -58,20 +52,18 @@ pip install fastvideo
 Please see our [docs](https://hao-ai-lab.github.io/FastVideo/getting_started/installation/) for more detailed installation instructions.

 ## Sparse Distillation
-
 For our sparse distillation techniques, please see our [distillation docs](https://hao-ai-lab.github.io/FastVideo/distillation/dmd/) and check out our [blog](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/).

 See below for recipes and datasets:

-| Model                                                                                 | Sparse Distillation                                                                                             | Dataset                                                                                                  |
-| ------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- |
-| [FastWan2.1-T2V-1.3B](https://huggingface.co/FastVideo/FastWan2.1-T2V-1.3B-Diffusers) | [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P)       | [FastVideo Synthetic Wan2.1 480P](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x448x832_600k)     |
-| [FastWan2.2-TI2V-5B](https://huggingface.co/FastVideo/FastWan2.2-TI2V-5B-Diffusers)   | [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free) | [FastVideo Synthetic Wan2.2 720P](https://huggingface.co/datasets/FastVideo/Wan2.2-Syn-121x704x1280_32k) |
+|                                            Model                                              |                                               Sparse Distillation                                                 |                                                  Dataset                                                  |
+|:-------------------------------------------------------------------------------------------:  |:---------------------------------------------------------------------------------------------------------------:  |:--------------------------------------------------------------------------------------------------------: |
+| [FastWan2.1-T2V-1.3B](https://huggingface.co/FastVideo/FastWan2.1-T2V-1.3B-Diffusers)         |    [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P)      | [FastVideo Synthetic Wan2.1 480P](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x448x832_600k)      |
+| [FastWan2.1-T2V-14B-Preview](https://huggingface.co/FastVideo/FastWan2.1-T2V-14B-Diffusers)   |                                                   Coming soon!                                                    |   [FastVideo Synthetic Wan2.1 720P](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k)   |
+| [FastWan2.2-TI2V-5B](https://huggingface.co/FastVideo/FastWan2.2-TI2V-5B-Diffusers)           | [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free)   | [FastVideo Synthetic Wan2.2 720P](https://huggingface.co/datasets/FastVideo/Wan2.2-Syn-121x704x1280_32k)  |

 ## Inference
-
 ### Generating Your First Video
-
 Here's a minimal example to generate a video using the default settings. Make sure VSA kernels are [installed](https://hao-ai-lab.github.io/FastVideo/video_sparse_attention/installation/). Create a file called `example.py` with the following code:

 ```python
@@ -110,36 +102,55 @@ python example.py

 For a more detailed guide, please see our [inference quick start](https://hao-ai-lab.github.io/FastVideo/inference/inference_quick_start/).

-## More Guides
+### Other docs:

 - [Design Overview](https://hao-ai-lab.github.io/FastVideo/design/overview/)
+- [Contribution Guide](https://hao-ai-lab.github.io/FastVideo/getting_started/installation/)
+
+## Distillation and Finetuning
 - [Distillation Guide](https://hao-ai-lab.github.io/FastVideo/distillation/dmd/)
- [Contribution Guide](https://hao-ai-lab.github.io/FastVideo/contributing/overview/)
+<!-- - [Finetuning Guide](https://hao-ai-lab.github.io/FastVideo/training/finetune.html) -->

 ## Awesome work using FastVideo or our research projects

- [SGLang](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen): SGLang's diffusion inference functionality is based on a fork of FastVideo on Sept. 24, 2025.
- [DanceGRPO](https://github.com/XueZeyue/DanceGRPO): A unified framework to adapt Group Relative Policy Optimization (GRPO) to visual generation paradigms. Code based on FastVideo.
- [SRPO](https://github.com/Tencent-Hunyuan/SRPO): A method to directly align the full diffusion trajectory with fine-grained human preference. Code based on FastVideo.
- [DCM](https://github.com/Vchitect/DCM): Dual-expert consistency model for efficient and high-quality video generation. Code based on FastVideo.
- [Hunyuan Video 1.5](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5): A leading lightweight video generation model, where they proposed SSTA based on Sliding Tile Attention.
- [Kandinsky-5.0](https://github.com/kandinskylab/kandinsky-5): A family of diffusion models for video & image generation, where their NABLA attention includes a Sliding Tile Attention branch.
- [LongCat Video](https://github.com/meituan-longcat/LongCat-Video): A foundational video generation model with 13.6B parameters with block-sparse attention similar to Video Sparse Attention.
+- [SGLang](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen): SGLang's diffusion inference functionality is based  on a fork of FastVideo on Sept. 24, 2025. [![Star](https://img.shields.io/github/stars/sgl-project/sglang.svg?style=social&label=Star)](https://github.com/sgl-project/sglang)
+
+- [DanceGRPO](https://github.com/XueZeyue/DanceGRPO): A  unified framework to adapt Group Relative Policy Optimization (GRPO) to visual generation paradigms. Code based on FastVideo. [![Star](https://img.shields.io/github/stars/XueZeyue/DanceGRPO.svg?style=social&label=Star)](https://github.com/XueZeyue/DanceGRPO)
+- [SRPO](https://github.com/Tencent-Hunyuan/SRPO): A method to directly align the full diffusion trajectory with fine-grained human preference. Code based on FastVideo. [![Star](https://img.shields.io/github/stars/Tencent-Hunyuan/SRPO.svg?style=social&label=Star)](https://github.com/Tencent-Hunyuan/SRPO)
+- [DCM](https://github.com/Vchitect/DCM): Dual-expert consistency model for efficient and high-quality video generation. Code based on FastVideo. [![Star](https://img.shields.io/github/stars/Vchitect/DCM.svg?style=social&label=Star)](https://github.com/Vchitect/DCM)
+- [Hunyuan Video 1.5](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5): A leading lightweight video generation model, where they proposed SSTA based on Sliding Tile Attention. [![Star](https://img.shields.io/github/stars/Tencent-Hunyuan/HunyuanVideo-1.5.svg?style=social&label=Star)](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5)
+- [Kandinsky-5.0](https://github.com/kandinskylab/kandinsky-5): A family of diffusion models for video & image generation, where their NABLA attention includes a Sliding Tile Attention branch. [![Star](https://img.shields.io/github/stars/kandinskylab/kandinsky-5.svg?style=social&label=Star)](https://github.com/kandinskylab/kandinsky-5)
+- [LongCat Video](https://github.com/meituan-longcat/LongCat-Video): A foundational video generation model with 13.6B parameters with block-sparse attention similar to Video Sparse Attention. [![Star](https://img.shields.io/github/stars/meituan-longcat/LongCat-Video.svg?style=social&label=Star)](https://github.com/meituan-longcat/LongCat-Video)

 ## 🤝 Contributing

 We welcome all contributions. Please check out our guide [here](https://hao-ai-lab.github.io/FastVideo/contributing/overview/).
 See details in [development roadmap](https://github.com/hao-ai-lab/FastVideo/issues/899).
-
 ## Acknowledgement
+We learned and reused code from the following projects:
+- [Wan-Video](https://github.com/Wan-Video)
+- [ThunderKittens](https://github.com/HazyResearch/ThunderKittens)
+- [Triton](https://github.com/triton-lang/triton)
+- [DMD2](https://github.com/tianweiy/DMD2)
+- [diffusers](https://github.com/huggingface/diffusers)
+- [xDiT](https://github.com/xdit-project/xDiT)
+- [vLLM](https://github.com/vllm-project/vllm)
+- [SGLang](https://github.com/sgl-project/sglang)

-We learned the design and reused code from the following projects: [Wan-Video](https://github.com/Wan-Video), [ThunderKittens](https://github.com/HazyResearch/ThunderKittens), [DMD2](https://github.com/tianweiy/DMD2), [diffusers](https://github.com/huggingface/diffusers), [xDiT](https://github.com/xdit-project/xDiT), [vLLM](https://github.com/vllm-project/vllm), [SGLang](https://github.com/sgl-project/sglang). We thank [MBZUAI](https://ifm.mbzuai.ac.ae/), [Anyscale](https://www.anyscale.com/), and [GMI Cloud](https://www.gmicloud.ai/) for their support throughout this project.
+We thank [MBZUAI](https://ifm.mbzuai.ac.ae/), [Anyscale](https://www.anyscale.com/), and [GMI Cloud](https://www.gmicloud.ai/) for their support throughout this project.

 ## Citation
-
-If you find FastVideo useful, please consider citing our research work:
+If you find FastVideo useful, please considering citing our work:

 ```bibtex
+@software{fastvideo2024,
+  title        = {FastVideo: A Unified Framework for Accelerated Video Generation},
+  author       = {The FastVideo Team},
+  url          = {https://github.com/hao-ai-lab/FastVideo},
+  month        = apr,
+  year         = {2024},
+}
+
@article{zhang2025vsa,
  title={Vsa: Faster video diffusion with trainable sparse attention},
  author={Zhang, Peiyuan and Chen, Yongqi and Huang, Haofeng and Lin, Will and Liu, Zhengzhong and Stoica, Ion and Xing, Eric and Zhang, Hao},
@@ -43,7 +43,7 @@ RUN source $HOME/.local/bin/env && \
    source /opt/venv/bin/activate && \
    uv pip install --no-cache-dir --upgrade pip && \
    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp310-cp310-linux_x86_64.whl
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3%2Bcu128torch2.9-cp310-cp310-linux_x86_64.whl

 COPY . .

@@ -43,7 +43,7 @@ RUN source $HOME/.local/bin/env && \
    source /opt/venv/bin/activate && \
    uv pip install --no-cache-dir --upgrade pip && \
    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp311-cp311-linux_x86_64.whl
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3%2Bcu128torch2.9-cp311-cp311-linux_x86_64.whl

 COPY . .

@@ -43,7 +43,7 @@ RUN source $HOME/.local/bin/env && \
    source /opt/venv/bin/activate && \
    uv pip install --no-cache-dir --upgrade pip && \
    uv pip install --no-cache-dir .[dev] && \
-    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.10-cp312-cp312-linux_x86_64.whl
+    uv pip install --no-cache-dir https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3%2Bcu128torch2.9-cp312-cp312-linux_x86_64.whl

 COPY . .

@@ -121,15 +121,6 @@ This page contains the complete API reference for the FastVideo library.
      show_root_toc_entry: true
      heading_level: 4

-## fastvideo.registry
-
-::: fastvideo.registry
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 3
-
 ## fastvideo.pipelines

 ::: fastvideo.pipelines
@@ -50,25 +50,21 @@ class MyNewAttnBackend(AttentionBackend):
 FastVideo uses a `ForwardContext` to pass global metadata (like current timestep, batch info, or custom attention configurations) to attention backends without changing the `forward` signature of every layer. **This is optional and only required if your backend needs dynamic per-step information.**

 To use this:
-
 1. **Set Context**: In your pipeline or generation loop, use the `set_forward_context` context manager.
 2. **Access Context**: Inside your attention backend, use `get_forward_context()`.

-See [`docs/attention/sta/index.md`](../sta/index.md) (Sliding Tile Attention) for an example of how complex configuration (window sizes) is passed this way.
+See `docs/attention/sta/index.md` (Sliding Tile Attention) for an example of how complex configuration (window sizes) is passed this way.

 ## 3. Adding Compiled Kernels (C++/CUDA)

 If your backend requires custom CUDA kernels, you need to add them to the `fastvideo-kernel` package.

 ### A. Add Source Files
-
 Place your kernel implementation files in `fastvideo-kernel/csrc/attention/`.
-
 * `mynew_attn.cu` (CUDA implementation)
 * `mynew_attn.h` (Optional headers)

 ### B. Register in Extension
-
 Update `fastvideo-kernel/csrc/common_extension.cpp` to expose your function to Python.

 ```cpp
@@ -88,7 +84,6 @@ PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
 ```

 ### C. Update CMakeLists.txt
-
 Update `fastvideo-kernel/CMakeLists.txt` to compile your new files.

 **Case 1: General CUDA Kernel (Runs on all GPUs)**
@@ -116,7 +111,6 @@ endif()
 ```

 ### D. Expose in Python Ops
-
 Update `fastvideo-kernel/python/fastvideo_kernel/ops.py` to make the function importable and handle fallbacks gracefully.

 ```python
@@ -139,7 +133,6 @@ def my_compiled_attn_func(q, k, v):
 ```

 ### E. Expose in Package Init
-
 Update `fastvideo-kernel/python/fastvideo_kernel/__init__.py` to export the function.

 ```python
@@ -6,8 +6,6 @@ FastVideo provides highly optimized custom attention kernels to accelerate video

 * **[Video Sparse Attention (VSA)](vsa/index.md)**: Sparse attention mechanism selecting top-k blocks.
 * **[Sliding Tile Attention (STA)](sta/index.md)**: Optimized attention for window-based video generation.
-* **Backend development guide**: See the developer guide at
-  [Attention Backend Development](../contributing/attention_backend.md).

 ## General Build Instructions

@@ -43,7 +41,7 @@ Clone the repository and build the kernel:

 ```bash
 # Clone recursively to get ThunderKittens submodule
-git clone https://github.com/hao-ai-lab/FastVideo.git
+git clone --recursive https://github.com/hao-ai-lab/FastVideo.git
 cd FastVideo/fastvideo-kernel

 # Build and install
@@ -13,13 +13,11 @@ from fastvideo_kernel import video_sparse_attn

 # q, k, v: [batch_size, num_heads, seq_len, head_dim]
 # variable_block_sizes: Number of valid tokens per block
-# q_variable_block_sizes: Number of valid tokens per q block (can differ from KV for q/k of different lengths)
 # topk: Number of blocks to attend

 output = video_sparse_attn(
    q, k, v, 
-    block_sizes,
-    block_sizes,
+    variable_block_sizes=block_sizes, 
    topk=32
 )
 ```
@@ -1,176 +0,0 @@
-# Attention Backend Development
-
-This guide is for contributors adding a new attention backend (kernel or
-implementation) to FastVideo. If you just want to use existing kernels or build
-fastvideo-kernel, see [Attention overview](../attention/index.md).
-
-## When you need this guide
-
-Use this guide when you are:
-
- Adding a new attention kernel or algorithm.
- Wiring an existing kernel into FastVideo's attention selection.
- Extending attention support to a new platform.
-
-## 0) Choose a backend name and scope
-
-Pick a backend name in `UPPER_SNAKE_CASE` and decide where it should run.
-Example: `MY_NEW_ATTN`.
-
-You will use this name in:
-
- `AttentionBackendEnum` (global list of backends).
- `get_name()` in your backend class (match the enum name).
- Platform selectors (CUDA/ROCm/MPS/NPU) to return your backend class.
-
-## 1) Add enum + platform selection
-
-1) Add your backend to `fastvideo/platforms/interface.py`:
-
-```python
-class AttentionBackendEnum(enum.Enum):
-    ...
-    MY_NEW_ATTN = enum.auto()
-```
-
-1) Register it in platform selection (example: CUDA). Update
-`fastvideo/platforms/cuda.py` inside `get_attn_backend_cls`:
-
-```python
-elif selected_backend == AttentionBackendEnum.MY_NEW_ATTN:
-    try:
-        from fastvideo.attention.backends.my_new_attn import MyNewAttnBackend
-        return "fastvideo.attention.backends.my_new_attn.MyNewAttnBackend"
-    except ImportError as e:
-        logger.error("Failed to import MY_NEW_ATTN backend: %s", str(e))
-        raise
-```
-
-If you want support on other platforms, add a similar branch in
-`fastvideo/platforms/rocm.py`, `fastvideo/platforms/mps.py`, or `fastvideo/platforms/npu.py`.
-
-## 2) Implement the backend
-
-Create `fastvideo/attention/backends/my_new_attn.py` and implement the required
-classes.
-
-Minimal skeleton (no custom metadata):
-
-```python
-import torch
-from dataclasses import dataclass
-from fastvideo.attention.backends.abstract import (
-    AttentionBackend,
-    AttentionImpl,
-    AttentionMetadata,
-    AttentionMetadataBuilder,
-)
-
-class MyNewAttnBackend(AttentionBackend):
-    @staticmethod
-    def get_name() -> str:
-        return "MY_NEW_ATTN"
-
-    @staticmethod
-    def get_impl_cls() -> type["MyNewAttnImpl"]:
-        return MyNewAttnImpl
-
-    @staticmethod
-    def get_metadata_cls() -> type["AttentionMetadata"]:
-        return AttentionMetadata
-
-    @staticmethod
-    def get_builder_cls() -> type["AttentionMetadataBuilder"]:
-        return MyNewAttnMetadataBuilder
-
-
-@dataclass
-class MyNewAttnMetadata(AttentionMetadata):
-    current_timestep: int
-
-
-class MyNewAttnMetadataBuilder(AttentionMetadataBuilder):
-    def __init__(self) -> None:
-        pass
-
-    def prepare(self) -> None:
-        pass
-
-    def build(self, current_timestep: int, **kwargs):
-        return MyNewAttnMetadata(current_timestep=current_timestep)
-
-
-class MyNewAttnImpl(AttentionImpl):
-    def __init__(
-        self,
-        num_heads: int,
-        head_size: int,
-        softmax_scale: float,
-        causal: bool = False,
-        num_kv_heads: int | None = None,
-        prefix: str = "",
-        **extra_impl_args,
-    ) -> None:
-        self.softmax_scale = softmax_scale
-        self.causal = causal
-
-    def forward(
-        self,
-        query: torch.Tensor,
-        key: torch.Tensor,
-        value: torch.Tensor,
-        attn_metadata: MyNewAttnMetadata,
-    ) -> torch.Tensor:
-        # Implement attention
-        return torch.nn.functional.scaled_dot_product_attention(
-            query.transpose(1, 2),
-            key.transpose(1, 2),
-            value.transpose(1, 2),
-            is_causal=self.causal,
-            scale=self.softmax_scale,
-        ).transpose(1, 2)
-```
-
-Optional:
-
- Implement `preprocess_qkv` / `postprocess_output` if your kernel needs tiling
-  or reshaping.
- Use `fastvideo.forward_context.get_forward_context()` if you need dynamic
-  per-step data (e.g., window sizes).
- Set `accept_output_buffer = True` if your backend writes into a provided
-  output buffer.
-
-## 3) Wire into attention layers
-
-Backends are used by `LocalAttention` and `DistributedAttention`. These layers
-accept a `supported_attention_backends` tuple. If your backend should be
-eligible, update the call sites that construct these layers (search for
-`supported_attention_backends=`).
-
-## 4) Add compiled kernels (optional)
-
-If you have a custom CUDA kernel:
-
-1) Add sources in `fastvideo-kernel/csrc/attention/`.
-2) Register bindings in `fastvideo-kernel/csrc/common_extension.cpp`.
-3) Add to `fastvideo-kernel/CMakeLists.txt` (and any feature flags).
-4) Expose in `fastvideo-kernel/python/fastvideo_kernel/ops.py`.
-5) Export in `fastvideo-kernel/python/fastvideo_kernel/__init__.py`.
-
-Keep a Python/Triton fallback so the backend runs even when the kernel is not
-available.
-
-## 5) Testing and debugging
-
- Add a small parity test or microbenchmark comparing to SDPA.
- Force your backend with the env var:
-  `FASTVIDEO_ATTENTION_BACKEND=MY_NEW_ATTN`.
- Check logs from `fastvideo/attention/selector.py` to confirm selection.
-
-## Checklist
-
- [ ] Added enum entry in `fastvideo/platforms/interface.py`.
- [ ] Implemented backend in `fastvideo/attention/backends/`.
- [ ] Registered selection in platform(s).
- [ ] Updated layer call sites to include the backend where appropriate.
- [ ] Added tests and documentation.
@@ -1,480 +0,0 @@
-# FastVideo + Coding Agents
-
-Coding agents are now strong at navigating large codebases and iterating fast
-with parity tests and examples. This guide shows how to use them to add new
-model pipelines and ship PRs in a production-grade video diffusion framework.
-
-FastVideo is a great project to contribute to, with production-grade
-infrastructure, active collaborations (including NVIDIA), and a pipeline design
-and inference architecture that has been forked by [SGLang’s
-multimodal generation stack](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen).
-
-Goal: run the new pipeline with a minimal script like
-`examples/inference/basic/basic.py`. In production, FastVideo can download
-models automatically via `HF_HOME`; for development, use local directories so
-agents can run scripts and tests deterministically. We standardize local paths
-as:
-
- `official_weights/<model_name>/` for official checkpoints
- `converted_weights/<model_name>/` if conversion is required
-
-## Tips when prompting the agent
-
-When prompting the agent, include:
-
- This guide and the [FastVideo design overview](../design/overview.md).
- Exact file paths to edit.
- A closest reference example file in FastVideo.
- Expected behavior and acceptance criteria.
- Repro steps (command, inputs, logs).
- Constraints (performance, memory, compatibility).
- Local paths (e.g., `official_weights/<model_name>/` or
-  `converted_weights/<model_name>/`) for parity tests.
-
-## FastVideo structure at a glance
-
-Before diving in, scan these references:
-
- [Contributing overview](overview.md) for environment/setup context.
- [FastVideo design overview](../design/overview.md) for pipeline architecture, configs, and HF layout.
-
-FastVideo maps a Diffusers-style repo into a pipeline like:
-
- `fastvideo/models/*`: model implementations (DiT, VAE, encoders, upsamplers).
- `fastvideo/configs/models/*`: arch configs and `param_names_mapping` for
-  weight name translation.
- `fastvideo/configs/pipelines/*`: pipeline wiring (component classes + names).
- `fastvideo/configs/sample/*`: default runtime sampling parameters.
- `fastvideo/pipelines/basic/*`: end-to-end pipeline logic built from stages.
- `model_index.json`: the HF repo entrypoint that maps component names to
-  classes and weight files.
- Component loading happens in `VideoGenerator.from_pretrained`, which reads
-  `model_index.json`, resolves configs, and loads weights.
-
-Minimal usage example (based on `examples/inference/basic/basic.py`):
-
-```python
-from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
-
-model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"  # or official_weights/<model_name>/
-generator = VideoGenerator.from_pretrained(model_id, num_gpus=1)
-
-sampling = SamplingParam.from_pretrained(model_id)
-sampling.num_frames = 45
-video = generator.generate_video(
-    "A vibrant city street at sunset.",
-    sampling_param=sampling,
-    output_path="video_samples",
-    save_video=True,
-)
-```
-
-## Some questions to ask yourself before starting
-
-Answering these upfront clarifies the work and speeds up implementation.
-
-### Is the model already supported by SGLang's multimodal generation stack?
-If yes, you can port many components from SGLang. It is a FastVideo fork, so
-interfaces line up, but you still need to swap layers/modules to match
-FastVideo's architecture and attention stack.
-
-If not, implement the model directly in FastVideo.
-
-### Is there an official implementation of the model you are adding?
-
-If yes, use it as the numerical reference. For example, LTX‑2 has an official
-implementation here: https://github.com/Lightricks/LTX-2. Prefer official code
-even if Diffusers also has one.
-
-### Is there a HuggingFace repo for the model you are adding? Is it in Diffusers format?
-
-If yes, load it directly in FastVideo after setting tensor mapping rules in the
-config. Otherwise, convert the weights to Diffusers format. See [Weights and
-Diffusers format](../design/overview.md#weights-and-diffusers-format) for details.
-
-### Do I have official weights + local paths ready?
-
-Standardize local paths as:
-
- `official_weights/<model_name>/` for official checkpoints
- `converted_weights/<model_name>/` if conversion is required (can be created later)
-
-### What pipeline components are required for the model you are adding?
-
-Usually you need a transformer (DiT), VAE, text encoder, and tokenizer. Some
-models add extra components.
-
-### What tasks does the model support?
-
-Usually a video diffusion model supports text‑to‑video (T2V),
-image‑to‑video (I2V), and video‑to‑video (V2V). Some add extra tasks (two‑stage
-generation, keyframe interpolation), which require extra components.
-
-It's usually easiest to start with a T2V pipeline and add the other tasks later.
-
-You can refer to the [Pipeline system](../design/overview.md#pipeline-system)
-section for more details.
-
-### Am I able to generate videos with the official implementation?
-
-These videos and prompts are your reference. Once the FastVideo pipeline works,
-compare outputs to the official implementation. Due to seeding and other
-factors, outputs may not match exactly, but they should be comparable.
-
-## Workflow: adding a full pipeline
-
-This is an example workflow for adding a full model pipeline (model + configs +
-examples + tests). This guide is in active development; feedback is welcome.
-
-!!! note
-    If you get stuck, refer to existing models/pipelines in FastVideo or ask in Slack.
-
-### 0) Fetch official model's code and weights
-
-Purpose:
-
- Keep official checkpoints and source code local so conversion, parity tests,
-  and reference runs are reproducible.
- Clone the official repo so you can use it as a numerical reference.
-
-Action:
-
- Download official weights into `official_weights/<model_name>/`
-  (Diffusers format or not).
- Clone the official repo under the project root (e.g., `FastVideo/LTX-2/`).
- If a Diffusers-format HF repo already exists, you can skip manual weight
-  handling and download it directly with
-  `scripts/huggingface/download_hf.py`.
-
-!!! note
-    This step is best done manually because large downloads can time out.
-    Example:
-    ```bash
-    python scripts/huggingface/download_hf.py \
-      --repo_id Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
-      --local_dir official_weights/Wan2.1-T2V-1.3B-Diffusers \
-      --repo_type model
-    ```
-  
-### 1) Implement the model + config mapping
-
-Purpose:
-
- Model weights are a dictionary of named tensors (`state_dict`). If the names
-  don’t line up with FastVideo’s module names, weights won’t load correctly (or
-  will silently load into the wrong layer).
- Official checkpoints often use different prefixes or module layouts than
-  FastVideo, so we translate names via the mapping (during load or conversion).
- Mapping aligns three things:
-  1. the official implementation’s module names,
-  2. the checkpoint `state_dict` keys,
-  3. FastVideo’s model classes and layer naming conventions.
- If names don’t align, weights won’t load; implement the FastVideo model and
-  define mapping rules first.
-
-Action:
-
- Implement the FastVideo model + config mapping.
-  - Add/extend the model in `fastvideo/models/...` and config in
-    `fastvideo/configs/models/...` (including `param_names_mapping`).
-  - Reuse existing FastVideo layers/modules where possible.
-  - Use FastVideo’s attention layers:
-    - `DistributedAttention` only for full‑sequence self‑attention in the DiT.
-    - `LocalAttention` for cross‑attention and other attention layers.
-  - See the “Configuration System” and “Weights and Diffusers format” sections
-    in `docs/design/overview.md` for how these pieces connect.
-  - If you are using an agent, ask it to implement the model, config mapping,
-    and a parity test together so you can validate numerics immediately.
-
-!!! note
-    After the first component is aligned and parity‑tested, open a **DRAFT PR**
-    on FastVideo so the rest of the pipeline work can build on top of it.
-
-!!! note
-    If a Diffusers-format HF repo already exists and loads correctly, you can
-    skip conversion entirely (no conversion script needed) and just download it
-    with `scripts/huggingface/download_hf.py`. Otherwise, you may need a
-    conversion script + a `converted_weights/<model>/` staging directory.
-
-Example (key renaming via arch config mapping, Wan2.1‑style):
-
-```python
-# Official model (simplified) in the upstream repo.
-class OfficialWanTransformer(torch.nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.patch_embedding = torch.nn.Conv3d(16, 1536, kernel_size=2, padding=0)
-
-    def forward(self, x):
-        return self.patch_embedding(x)
-
-# FastVideo model (simplified) in fastvideo/models/dits/wanvideo.py
-class PatchEmbed(torch.nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.proj = torch.nn.Conv3d(16, 1536, kernel_size=2, padding=0)
-
-    def forward(self, x):
-        return self.proj(x)
-
-class WanTransformer3DModel(torch.nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.patch_embedding = PatchEmbed()
-
-    def forward(self, x):
-        return self.patch_embedding(x)
-
-# Mapping defined in a config (simplified; see the real mapping in
-# fastvideo/configs/models/dits/wanvideo.py)
-param_names_mapping = {
-    r"^patch_embedding\.(.*)$": r"patch_embedding.proj.\1",
-    r"^blocks\.(\d+)\.attn1\.to_q\.(.*)$": r"blocks.\1.to_q.\2",
-}
-
-def apply_regex_map(state_dict, mapping):
-    # Pseudocode: apply regex substitutions in order
-    ...
-
-# Official checkpoint keys (example)
-official = {
-    "patch_embedding.weight": ...,
-    "blocks.0.attn1.to_q.weight": ...,
-}
-
-# Apply mapping so keys match FastVideo modules
-converted = apply_regex_map(official, param_names_mapping)
-
-```
-
-Optional helper (print a few checkpoint keys quickly):
-
-```bash
-python - <<'PY'
-import safetensors.torch as st
-keys = list(st.load_file("official_weights/<model>/transformer/diffusion_pytorch_model.safetensors").keys())
-print(keys[:20])
-PY
-```
-
-Example agent prompt (task request):
-
-```
-Please add the Wan2.1 T2V 1.3B Diffusers pipeline to FastVideo:
- Add a FastVideo native Wan2.1 DiT implementation + config mapping.
- Make sure to use the existing FastVideo layers and attention modules where possible.
- Add a parity test that loads the official model alongside the FastVideo model and compares outputs numerically with fixed seeds and inputs.
-
-Paths:
-  - Official repo: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
-  - Local download: official_weights/Wan2.1-T2V-1.3B-Diffusers
-Mapping steps:
-  - Load the official DiT weights from
-    official_weights/Wan2.1-T2V-1.3B-Diffusers/transformer/diffusion_pytorch_model.safetensors.
-  - Instantiate the FastVideo DiT (`WanTransformer3DModel`) and compare
-    its `state_dict().keys()` to the official keys.
-  - Update `param_names_mapping` in
-    fastvideo/configs/models/dits/wanvideo.py to resolve missing/unexpected keys.
-  - Use `load_state_dict(strict=False)` during iteration to surface mismatches.
-```
-
-External examples of the same pattern:
- SGLang uses prefix-based routing in its weight loader to map checkpoint keys
-  into internal submodules (e.g., stripping a top-level prefix before delegating).
- vLLM includes model-specific renamers for certain checkpoints that adjust
-  key prefixes so weights match its internal naming.
-
-### 2) Test numerical alignment with the official implementation
-
-Purpose:
-
- Verify that the FastVideo component is numerically aligned with the official
-  implementation.
-
-Action:
-
- Add or reuse a numerical parity test that loads the official model and the
-  FastVideo model and compares outputs.
- See examples in `tests/local_tests/` (e.g., `tests/local_tests/upsamplers/`)
-  and the commands in `tests/local_tests/README.md`.
- If there are discrepancies, add opt‑in logging to both models and compare
-  activation summaries (layer output sums, per‑stage logs).
- First align the loaded weights (validate `param_names_mapping`).
- Then align forward outputs using fixed seeds and inputs.
-  - Start with `atol=1e-4, rtol=1e-4` in `assert_close`.
-  - Keep dtype consistent (bf16 if available; otherwise fp32).
-  - If attention parity is unstable, align backends (e.g.,
-    `FASTVIDEO_ATTENTION_BACKEND=TORCH_SDPA`).
-
-### 3) Repeat the process for each component
-
-If the model requires additional components, repeat Steps 1–2 for each one.
-For example, implement the VAE in `fastvideo/models/vaes/` and its config in
-`fastvideo/configs/models/vaes/`, then add parity coverage for it.
-
-### 4) Add a pipeline config + sample defaults
-
-Purpose:
-
- `fastvideo/configs/pipelines/` describes pipeline wiring and model module
-  names.
- `fastvideo/configs/sample/` defines default runtime parameters.
-
-Action:
-
- Add a new pipeline config + sampling params.
- Register them in `fastvideo/registry.py` using explicit
-  `register_configs(...)` blocks (this file is the single source of truth now).
-
-### 5) Wire pipeline stages
-
-Purpose:
-
- `fastvideo/pipelines/basic/<pipeline>/` contains the actual pipeline logic.
- `fastvideo/pipelines/stages/` holds reusable, testable stages.
-
-Action:
-
- Build the pipeline using stages; keep new stages isolated and documented.
- Prefer opt‑in flags for expensive or optional steps.
-
-### 6) Add pipeline‑level tests
-
-Purpose:
-
- Ensure the end‑to‑end pipeline works and stays aligned as pieces evolve.
-
-Action:
-
- Add a pipeline parity test under `tests/local_tests/pipelines/`.
- See the [Testing Guide](testing.md) for test conventions.
-
-### 7) Add user‑facing examples
-
-Purpose:
-
- `examples/inference/basic/` is the entry point for simple, runnable scripts.
-
-Action:
-
- Provide a minimal “hello world” example plus advanced variations.
- Use fixed seeds and stable prompts.
- Run the example locally to confirm end‑to‑end behavior.
-
-### 8) Add SSIM tests for CI checks
-
-Purpose:
-
- Ensure visual similarity stays within expected bounds for regression testing.
- SSIM tests act as a higher‑level guardrail beyond unit/parity tests.
-
-Action:
-
- Add SSIM tests under `fastvideo/tests/ssim/` and include reference videos
-  (see the structure in the Testing Guide).
- Use stable prompts/seeds and document any GPU‑specific requirements.
- Follow the [Testing Guide](testing.md) for reference video placement and
-  execution details.
-
-### 9) Document it
-
-Purpose:
-
- `docs/` is where users find the new pipeline usage and limitations.
-
-Action:
-
- Add a short doc page or update an existing one.
- Mention any caveats (memory, speed, constraints).
-
-## Common pitfalls when porting models
-
- **Attention backend mismatch**: parity can fail if the official model uses a
-  different attention backend (e.g., SDPA vs custom). Align backends before
-  debugging deeper issues.
- **Patchifier shape mistakes**: wrong patchification or reshape lengths can
-  silently corrupt outputs. Validate patch shapes early.
- **Mask handling**: attention masks must match the official behavior (padding,
-  causal masks, and broadcast shapes).
- **Scheduler / sigma schedule mismatch**: even small differences in schedules
-  or timestep shapes can cause noticeable drift.
-
-## Diffusers vs manual conversion
-
-If a model already ships in Diffusers format (with a proper `model_index.json`),
-prefer downloading it directly and loading it via FastVideo. In that case:
-
- You usually **do not need** a conversion script.
- You still need a correct `param_names_mapping` if the internal module names
-  differ from FastVideo’s implementation.
-
-If the model does **not** have a Diffusers-format repo:
-
- You will need a conversion script to rewrite `state_dict` keys into FastVideo
-  naming and stage the result (e.g., under `converted_weights/<model>/`).
- You may still use the official repo for reference parity and debugging.
-
-In both cases, parity testing is required to validate correctness.
-
-If you want to publish a Diffusers‑style repo after conversion, use
-`scripts/checkpoint_conversion/create_hf_repo.py` to assemble a HuggingFace‑ready
-directory before uploading.
-
-## FAQ
-
-**Q: Why do we implement the FastVideo model before conversion?**  
-A: You can’t define the key‑mapping rules until the FastVideo module names are
-known. The implementation determines the target `state_dict` schema.
-
-**Q: Do we always need a conversion script?**  
-A: No. If a Diffusers‑format repo exists and loads correctly, download it and
-skip conversion.
-
-**Q: How do I figure out `param_names_mapping` quickly?**  
-A: Load the official weights, instantiate the FastVideo model, and diff
-`state_dict().keys()` on both sides. Add regex rules until missing/unexpected
-keys are resolved. Agents can help you with this.
-
-**Q: What if parity fails even after mapping?**  
-A: Align attention backends, sigma schedules, and timestep shapes first. Then
-add opt‑in activation logging to locate the first divergent layer.
-
-## Case study: LTX‑2 port (from PLAN.md)
-
-The LTX‑2 port in `PLAN.md` shows the real sequence of steps and backtracking
-that happened during integration. Use it as a reference for how parity work
-actually unfolds:
-
- Ported components first (transformer, VAE, audio, text encoder).
- Added parity tests per component; used SDPA for reference parity.
- Added debug logging to compare per‑block activations and isolate divergence.
- Fixed cross‑attention reshape and patch grid bounds issues after logging.
- Aligned sigma schedule and masking behavior to match the official pipeline.
-
-Recommendation:
-
- Keep raw step‑by‑step logs in your own local `PLAN.md` for large ports.
-
-## Worked example: Wan2.1 T2V 1.3B pipeline
-
-The Wan2.1 T2V 1.3B Diffusers pipeline is a good “standard” example for
-FastVideo integration.
-
-1. Verify model config + mapping.
-   - DiT mapping: `fastvideo/configs/models/dits/wanvideo.py`
-   - VAE: `fastvideo/models/vaes/wanvae.py`
-   - Text encoder: `fastvideo/models/encoders/t5.py`
-
-2. Parity test the core components.
-   - Example tests: `fastvideo/tests/transformers/test_wanvideo.py`,
-     `fastvideo/tests/vaes/test_wan_vae.py`,
-     `fastvideo/tests/encoders/test_t5_encoder.py`
-
-3. Pipeline wiring.
-   - Pipeline: `fastvideo/pipelines/basic/wan/wan_pipeline.py`
-   - Pipeline config: `fastvideo/configs/pipelines/wan.py`
-   - Sampling defaults: `fastvideo/configs/sample/wan.py`
-
-4. Minimal example.
-   - Script: `examples/inference/basic/basic.py`
@@ -1,55 +1,16 @@

 # 📦 Developing FastVideo on RunPod

-You can easily use the FastVideo Pod Template on [RunPod](https://www.runpod.io) for development or experimentation.
+You can easily use the FastVideo Docker image as a custom container on [RunPod](https://www.runpod.io) for development or experimentation.

 ## Creating a new pod

- Make sure you are using the correct RunPod account.
-![RunPod Account Selection](../../assets/images/runpod_account.png)
+Choose a GPU that supports CUDA 12.8
+
+Pick 1 or 2 L40S GPU(s)

- Use "Additional Filters" to select CUDA 12.8.
 ![RunPod CUDA selection](../../assets/images/runpod_cuda.png)

- Click "Deploy" and Pick a single A40 or RTX 4090 GPU.
-![RunPod GPU Selection](../../assets/images/runpod_deploy.png)
-
- Select the "FastVideo" or "fastvideo-dev" Pod Template.
-![RunPod Pod Template Selection](../../assets/images/runpod_create.png)
-
- Set the Pod name to "`<name>-<FastVideo>-<date>`".
-
- Finally, once the pod is deployed (will take a few minutes as the image is being pulled), you can SSH into it using "SSH exposed over TCP". You'll need to use the matching private ssh key you provided.
-![RunPod SSH](../../assets/images/runpod_ssh.png)
-
-## Working with the pod
-
-After SSH'ing into your pod, you'll find the correct `uv` environment already activated and you should be in /FastVideo/ directory. Make sure to use /FastVideo/ for all your work.
-
-To pull in the latest changes from the GitHub repo:
-
-```bash
-cd /FastVideo
-git pull
-```
-
-Run your development workflows as usual:
-
-```bash
-# Run linters
-pre-commit run --all-files
-
-# Run tests
-pytest tests/
-```
-
-Make sure to push your changes back to the GitHub repo as nothing will be saved to the pod when it is terminated.
-
-After you are done with your work, you can terminate the pod by clicking the "Terminate" and "Delete" buttons. Remember if the pod is not completely deleted, Runpod will keep charging you for it.
-
-## Extra Information:
-If you need to customize the pod template this section has some useful information. For the most part you can leave the defaults of the FastVideo Pod Template.
-
 When creating your pod template, use this image:

 ```
@@ -63,3 +24,30 @@ bash -c "apt update;DEBIAN_FRONTEND=noninteractive apt-get install openssh-serve
 ```

 ![RunPod template configuration](../../assets/images/runpod_template.png)
+
+After deploying, the pod will take a few minutes to pull the image and start the SSH service.
+
+![RunPod ssh](../../assets/images/runpod_ssh.png)
+
+## Working with the pod
+
+After SSH'ing into your pod, you'll find the `fastvideo-dev` Conda environment already activated.
+
+To pull in the latest changes from the GitHub repo:
+
+```bash
+cd /FastVideo
+git pull
+```
+
+`If you have a persistent volume and want to keep your code changes, you can move /FastVideo to /workspace/FastVideo, or simply clone the repository there.`
+
+Run your development workflows as usual:
+
+```bash
+# Run linters
+pre-commit run --all-files
+
+# Run tests
+pytest tests/
+```
@@ -1,84 +1,76 @@

 # 🛠️ Contributing to FastVideo

-Thank you for your interest in contributing to FastVideo. We want the process
-to be smooth and beginner‑friendly, whether you are adding a new pipeline,
-improving performance, or fixing a bug.
+Thank you for your interest in contributing to FastVideo. We want to make the process as smooth for you as possible and this is a guide to help get you started!

-## Quick prerequisites
+Our community is open to everyone and welcomes any contributions no matter how large or small.

- **OS**: Linux is the primary development target (WSL can work).
- **GPU**: NVIDIA GPU recommended for inference and training workflows.
- **CUDA**: Use a recent CUDA 12.x toolchain (see the installation guide for
-  the current recommendation).
+# Developer Environment:
+Do make sure you have CUDA 12.4 installed and supported. FastVideo currently only supports Linux and CUDA GPUs, but we hope to support other platforms in the future.

-For a full install checklist, see `docs/getting_started/installation/gpu.md`.
-
-## Local development (Conda + editable install)
+We recommend using a fresh Python 3.10 Conda environment to develop FastVideo:

 Install Miniconda:

-```bash
+```
 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
 bash Miniconda3-latest-Linux-x86_64.sh
 source ~/.bashrc
 ```

-Create and activate a Conda environment:
+Create and activate a Conda environment for FastVideo:

-```bash
+```
 conda create -n fastvideo python=3.12 -y
 conda activate fastvideo
 ```

 Install `uv` (optional, but recommended):

-```bash
+From instructions on [uv](https://astral.sh/uv/):
+
+```
 curl -LsSf https://astral.sh/uv/install.sh | sh
-# or
+# or 
 wget -qO- https://astral.sh/uv/install.sh | sh
 ```

-Clone the repo:
+Clone the FastVideo repository and go to the FastVideo directory:

-```bash
+```
 git clone https://github.com/hao-ai-lab/FastVideo.git && cd FastVideo
+
 ```

-Install FastVideo in editable mode and set up hooks:
+Now you can install FastVideo and setup git hooks for running linting. By using `pre-commit`, the linters will run and have to pass before you'll be able to make a commit.

 ```bash
 uv pip install -e .[dev]

-# Optional: FlashAttention (builds native kernels)
-uv pip install flash-attn --no-build-isolation
+# Can also install flash-attn (optional)
+uv pip install flash-attn --no-build-isolation 

-# Linting, formatting, static typing
+# Linting, formatting and static type checking
 pre-commit install --hook-type pre-commit --hook-type commit-msg
+
+# You can manually run pre-commit with
 pre-commit run --all-files

 # Unit tests
 pytest tests/
 ```

-If you are on a Hopper GPU, installing FlashAttention 3 can improve
-performance (see `docs/inference/optimizations.md`).
+If you are on a Hopper GPU, you should also install [FA3](https://github.com/Dao-AILab/flash-attention) for much better performance:

-## Docker development (optional)
+```
+git clone https://github.com/Dao-AILab/flash-attention.git && cd flash-attention/hopper

-If you prefer a containerized environment, use the dev image documented in
-`docs/contributing/developer_env/docker.md`.
+# make sure you have ninja installed
+uv pip install ninja
+
+python setup.py install
+```

 ## Testing

-See the [Testing Guide](testing.md) for how to add and run tests in FastVideo.
-
-## Attention backend development
-
-If you are adding a new attention kernel or backend, follow
-[Attention Backend Development](attention_backend.md).
-
-## Contributing with coding agents
-
-For a step‑by‑step workflow on adding pipelines or components with coding
-agents, see `docs/contributing/coding_agents.md`.
+Please refer to the [Testing Guide](testing.md) for more information on how to add and run tests in FastVideo.
@@ -1,179 +1,403 @@
-# FastVideo Architecture Overview
+# 🔍 FastVideo Overview

-This document summarizes how FastVideo is structured and how a Diffusers-style
-model repo maps into a runnable pipeline. It is intended for contributors who
-need the high-level layout and key entrypoints, not every internal detail.
+This document outlines FastVideo's architecture for developers interested in framework internals or contributions. It serves as an onboarding guide for new contributors by providing an overview of the most important directories and files within the `fastvideo/` codebase.

-## FastVideo structure at a glance
+## Table of Contents - Directory Structure and Files

-FastVideo maps a Diffusers-style repo into a pipeline like this:
+- [`fastvideo/pipelines/`](#design-pipeline-system) - Core diffusion pipeline components
+- [`fastvideo/models/`](#design-model-components) - Model implementations
+  - [`dits/`](#design-transformer-models) - Transformer-based diffusion models
+  - [`vaes/`](#design-vae-variational-auto-encoder) - Variational autoencoders
+  - [`encoders/`](#design-text-and-image-encoders) - Text and image encoders
+  - [`schedulers/`](#design-schedulers) - Diffusion schedulers
+- [`fastvideo/attention/`](#design-optimized-attention) - Optimized attention implementations
+- [`fastvideo/distributed/`](#design-distributed-processing) - Distributed computing utilities
+- [`fastvideo/layers/`](#design-tensor-parallelism) - Custom neural network layers
+- [`fastvideo/platforms/`](#design-platforms) - Hardware platform abstractions
+- [`fastvideo/worker/`](#design-executor-and-worker-abstractions) - Multi-GPU process management
+- [`fastvideo/fastvideo_args.py`](#design-fastvideo-args) - Argument handling
+- [`fastvideo/forward_context.py`](#design-forwardcontext) - Forward pass context management
+- `fastvideo/utils.py` - Utility functions
+- [`fastvideo/logger.py`](#design-logger) - Logging infrastructure

- `fastvideo/models/*`: model implementations (DiT, VAE, encoders, upsamplers).
- `fastvideo/configs/models/*`: arch configs and `param_names_mapping` for
-  weight name translation.
- `fastvideo/configs/pipelines/*`: pipeline wiring (component classes + names).
- `fastvideo/configs/sample/*`: default runtime sampling parameters.
- `fastvideo/pipelines/basic/*`: end-to-end pipelines.
- `fastvideo/pipelines/stages/*`: reusable pipeline stages.
- `fastvideo/models/loader/*`: component loaders for Diffusers-style repos.
- `model_index.json`: HF repo entrypoint mapping component names to classes.
+## Core Architecture

-Flow:
-`model_index.json` -> component loaders -> model modules -> pipeline stages ->
-sampling params.
+FastVideo separates model components from execution logic with these principles:
+- **Component Isolation**: Models (encoders, VAEs, transformers) are isolated from execution (pipelines, stages, distributed processing)
+- **Modular Design**: Components can be independently replaced
+- **Distributed Execution**: Supports various parallelism strategies (Tensor, Sequence)
+- **Custom Attention Backends**: Components can support and use different Attention implementations
+- **Pipeline Abstraction**: Consistent interface across diffusion models

-Minimal usage (from `examples/inference/basic/basic.py`):
+## FastVideoArgs
+
+The `FastVideoArgs` class in `fastvideo/fastvideo_args.py` serves as the central configuration system for FastVideo. It contains all parameters needed to control model loading, inference configuration, performance optimization settings, and more.
+
+Key features include:
+- **Command-line Interface**: Automatic conversion between CLI arguments and dataclass fields
+- **Configuration Groups**: Organized by functional areas (model loading, video params, optimization settings)
+- **Context Management**: Global access to current settings via `get_current_fastvideo_args()`
+- **Parameter Validation**: Ensures valid combinations of settings
+
+Common configuration areas:
+- **Model paths and loading options**: `model_path`, `trust_remote_code`, `revision`
+- **Distributed execution settings**: `num_gpus`, `tp_size`, `sp_size`
+- **Video generation parameters**: `height`, `width`, `num_frames`, `num_inference_steps`
+- **Precision settings**: Control computation precision for different components
+
+Example usage:

 ```python
-from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
+# Load arguments from command line
+fastvideo_args = prepare_fastvideo_args(sys.argv[1:])

-model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"  # or official_weights/<model_name>/
-generator = VideoGenerator.from_pretrained(model_id, num_gpus=1)
+# Access parameters
+model = load_model(fastvideo_args.model_path)

-sampling = SamplingParam.from_pretrained(model_id)
-sampling.num_frames = 45
-video = generator.generate_video(
-    "A vibrant city street at sunset.",
-    sampling_param=sampling,
-    output_path="video_samples",
-    save_video=True,
+# Set as global context
+with set_current_fastvideo_args(fastvideo_args):
+    # Code that requires access to these arguments
+    result = generate_video()
+```
+
+## Pipeline System
+
+### `ComposedPipelineBase`
+
+This foundational class provides:
+
+- **Model Loading**: Automatically loads components from HuggingFace-Diffusers-compatible model directories
+- **Stage Management**: Creates and orchestrates processing stages
+- **Data Flow Coordination**: Ensures proper state flow between stages
+
+```python
+class MyCustomPipeline(ComposedPipelineBase):
+    _required_config_modules = [
+        "text_encoder", "tokenizer", "vae", "transformer", "scheduler"
+    ]
+    
+    def initialize_pipeline(self, fastvideo_args: FastVideoArgs):
+        # Pipeline-specific initialization
+        pass
+        
+    def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
+        self.add_stage("input_validation_stage", InputValidationStage())
+        self.add_stage("text_encoding_stage", CLIPTextEncodingStage(
+            text_encoder=self.get_module("text_encoder"),
+            tokenizer=self.get_module("tokenizer")
+        ))
+        # Additional stages...
+```
+
+### Pipeline Stages
+Each stage handles a specific diffusion process component:
+- **Input Validation**: Parameter verification
+- **Text Encoding**: CLIP, LLaMA, or T5-based encoding
+- **Image Encoding**: Image input processing
+- **Timestep & Latent Preparation**: Setup for diffusion
+- **Denoising**: Core diffusion loop
+- **Decoding**: Latent-to-pixel conversion
+
+Each stage implements a standard interface:
+
+```python
+def forward(self, batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch:
+    # Process batch and update state
+    return batch
+```
+
+![Pipeline execution and data flow](../assets/images/pipeline.png)
+
+### ForwardBatch
+
+Defined in `fastvideo/pipelines/pipeline_batch_info.py`, `ForwardBatch` encapsulates the data payload passed between pipeline stages. It typically holds:
+
+- **Input Data**: Prompts, images, generation parameters
+- **Intermediate State**: Embeddings, latents, timesteps, accumulated during stage execution
+- **Output Storage**: Generated results and metadata
+- **Configuration**: Sampling parameters, precision settings
+
+This structure facilitates clear state transitions between stages.
+
+## Model Components
+
+The `fastvideo/models/` directory contains implementations of the core neural network models used in video diffusion:
+
+### Transformer Models
+
+Transformer networks perform the actual denoising during diffusion:
+
+- **Location**: `fastvideo/models/dits/`
+- **Examples**:
+  - `WanTransformer3DModel`
+  - `HunyuanVideoTransformer3DModel`
+
+Features include:
+- Text/image conditioning
+- Standardized interface for model-specific optimizations
+
+```python
+def forward(
+    self, 
+    latents,                    # [B, T, C, H, W]
+    encoder_hidden_states,      # Text embeddings
+    timestep,                   # Current diffusion timestep
+    encoder_hidden_states_image=None,  # Optional image embeddings
+    **kwargs
+):
+    # Perform denoising computation
+    return noise_pred  # Predicted noise residual
+```
+
+### VAE (Variational Auto-Encoder)
+
+VAEs handle conversion between pixel space and latent space:
+
+- **Location**: `fastvideo/models/vaes/`
+- **Examples**:
+  - `AutoencoderKLWan`
+  - `AutoencoderKLHunyuanVideo`
+
+These models compress image/video data to a more efficient latent representation (typically 4x-8x smaller in each dimension).
+
+FastVideo's VAE implementations include:
+- Efficient video batch processing
+- Memory optimization
+- Optional tiling for large frames
+- Distributed weight support
+
+### Text and Image Encoders
+
+Encoders process conditioning inputs into embeddings:
+
+- **Location**: `fastvideo/models/encoders/`
+- **Text Encoders**:
+  - `CLIPTextModel`
+  - `LlamaModel`
+  - `UMT5EncoderModel`
+- **Image Encoders**:
+  - `CLIPVisionModel`
+
+FastVideo implements optimizations such as:
+- Vocab parallelism for distributed processing
+- Caching for common prompts
+- Precision-tuned computation
+
+### Schedulers
+
+Schedulers manage the diffusion sampling process:
+
+- **Location**: `fastvideo/models/schedulers/`
+- **Examples**:
+  - `UniPCMultistepScheduler`
+  - `FlowMatchEulerDiscreteScheduler`
+
+These components control:
+- Diffusion timestep sequences
+- Noise prediction to latent update conversions
+- Quality/speed trade-offs
+
+```python
+def step(
+    self, 
+    model_output: torch.Tensor,
+    timestep: torch.LongTensor,
+    sample: torch.Tensor,
+    **kwargs
+) -> torch.Tensor:
+    # Process model output and update latents
+    # Return updated latents
+    return prev_sample
+```
+
+This diagram shows how models are discovered, validated, and loaded across entrypoints, executors, pipelines, and model loaders.
+
+![Model loading flow](../assets/images/load_models.png)
+
+## Optimized Attention
+
+The `fastvideo/attention/` directory contains optimized attention implementations crucial for efficient video diffusion:
+
+### Attention Backends
+Multiple implementations with automatic selection:
+- **FLASH_ATTN**: Optimized for supporting hardware
+- **TORCH_SDPA**: Built-in PyTorch scaled dot-product attention
+- **SLIDING_TILE_ATTN**: For very long sequences
+
+```python
+# Configure available attention backends for this layer
+self.attn = LocalAttention(
+    num_heads=num_heads,
+    head_size=head_dim,
+    causal=False,
+    supported_attention_backends=(_Backend.FLASH_ATTN, _Backend.TORCH_SDPA)
+)
+
+# Override via environment variable
+# export FASTVIDEO_ATTENTION_BACKEND=FLASH_ATTN
+```
+
+![Attention backend selector design](../assets/images/attention_backend.png)
+
+### Attention Patterns
+Supports various patterns with memory optimization techniques:
+- **Cross/Self/Temporal/Global-Local Attention**
+- Chunking, progressive computation, optimized masking
+
+## Distributed Processing
+
+The `fastvideo/distributed/` directory contains implementations for distributed model execution:
+
+### Tensor Parallelism
+
+Tensor parallelism splits model weights across devices:
+
+- **Implementation**: Through `RowParallelLinear` and `ColumnParallelLinear` layers
+- **Use cases**: Will be used by encoder models as their sequence lengths are shorter and enables efficient sharding.
+
+```python
+# Tensor-parallel layers in a transformer block
+from fastvideo.layers.linear import ColumnParallelLinear, RowParallelLinear
+
+# Split along output dimension
+self.qkv_proj = ColumnParallelLinear(
+    input_size=hidden_size,
+    output_size=3 * hidden_size,
+    bias=True,
+    gather_output=False
+)
+
+# Split along input dimension
+self.out_proj = RowParallelLinear(
+    input_size=hidden_size,
+    output_size=hidden_size,
+    bias=True,
+    input_is_parallel=True
 )
 ```

-## Configuration system
+### Sequence Parallelism

-FastVideo uses typed configs to keep model definitions, pipeline wiring, and
-runtime parameters consistent:
+Sequence parallelism splits sequences across devices:

- `fastvideo/configs/models/`: architecture definitions, layer shapes, and
-  `param_names_mapping` rules for key renaming.
- `fastvideo/configs/pipelines/`: pipeline wiring and required components.
- `fastvideo/configs/sample/`: default sampling parameters (steps, frames,
-  guidance scale, resolution, fps).
- `fastvideo/registry.py`: unified registry for pipeline config + sampling
-  defaults and model metadata resolution, defined via explicit
-  `register_configs(...)` blocks (no separate dict registries).
+- **Implementation**: Through `DistributedAttention` and sequence splitting
+- **Use cases**: Long video sequences or high-resolution processing. Used by DiT models.

-`FastVideoArgs` (in `fastvideo/fastvideo_args.py`) provides runtime settings and
-is passed into pipeline construction and stages.
+```python
+# Distributed attention for long sequences
+from fastvideo.attention import DistributedAttention

-## Weights and Diffusers format
-
-FastVideo follows the HuggingFace Diffusers repo layout. This keeps loaders
-compatible with HF repos and makes it easy to add new components.
-
-Typical Diffusers repo:
-
-```
-<model-repo>/
-  model_index.json
-  scheduler/
-    scheduler_config.json
-  transformer/               # or unet/ for image models
-    config.json
-    diffusion_pytorch_model.safetensors
-  vae/
-    config.json
-    diffusion_pytorch_model.safetensors
-  text_encoder/
-    config.json
-    model.safetensors
-  tokenizer/
-    tokenizer_config.json
-    tokenizer.json
+self.attn = DistributedAttention(
+    num_heads=num_heads,
+    head_size=head_dim,
+    causal=False,
+    supported_attention_backends=(_Backend.SLIDING_TILE_ATTN, _Backend.FLASH_ATTN)
+)
 ```

-Key points:
+### Communication Primitives
+Efficient distributed operations via AllGather, AllReduce, and synchronization mechanisms.

- `model_index.json` is the root map that tells FastVideo which components to
-  load and which classes implement them.
- Each component lives in its own folder with a `config.json` and weights.
- Weights are usually in `diffusion_pytorch_model.safetensors`.
+Efficient communication primitives minimize distributed overhead:

-Note on tensor names:
+- **Sequence-Parallel AllGather**: Collects sequence chunks
+- **Tensor-Parallel AllReduce**: Combines partial results
+- **Distributed Synchronization**: Coordinates execution

-Official checkpoints often use different `state_dict` names than FastVideo's
-module layout. We translate tensor names via the DiT arch config mapping
-(`param_names_mapping` under `fastvideo/configs/models/dits/`). This is similar
-in spirit to name-translation layers used in systems like vLLM and SGLang.
+## Forward Context Management

-Example HF repo (Wan 2.1 T2V 1.3B Diffusers):
+### ForwardContext

-```
-https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers/tree/main
+Defined in `fastvideo/forward_context.py`, `ForwardContext` manages execution-specific state *within* a forward pass, particularly for low-level optimizations. It is accessed via `get_forward_context()`.
+
+- **Attention Metadata**: Configuration for optimized attention kernels (`attn_metadata`)
+- **Profiling Data**: Potential hooks for performance metrics collection
+
+This context-based approach enables:
+- Dynamic optimization based on execution state (e.g., attention backend selection)
+- Step-specific customizations within model components
+
+Usage example:
+
+```python
+with set_forward_context(current_timestep, attn_metadata, fastvideo_args):
+    # During this forward pass, components can access context
+    # through get_forward_context()
+    output = model(inputs)
 ```

-Example `model_index.json` from that repo:
+## Executor and Worker System

-```json
-{
-  "_class_name": "WanPipeline",
-  "_diffusers_version": "0.33.0.dev0",
-  "scheduler": [
-    "diffusers",
-    "UniPCMultistepScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "UMT5EncoderModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "T5TokenizerFast"
-  ],
-  "transformer": [
-    "diffusers",
-    "WanTransformer3DModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKLWan"
-  ]
-}
+The `fastvideo/worker/` directory contains the distributed execution framework:
+
+### Executor Abstraction
+
+FastVideo implements a flexible execution model for distributed processing:
+
+- **Executor Base Class**: An abstract base class defining the interface for all executors
+- **MultiProcExecutor**: Primary implementation that spawns and manages worker processes
+- **GPU Workers**: Handle actual model execution on individual GPUs
+
+The MultiProcExecutor implementation:
+1. Spawns worker processes for each GPU
+2. Establishes communication channels via pipes
+3. Coordinates distributed operations across workers
+4. Handles graceful startup and shutdown of the process group
+
+Each GPU worker:
+1. Initializes the distributed environment
+2. Builds the pipeline for the specified model
+3. Executes requested operations on its assigned GPU
+4. Manages local resources and communicates results back to the executor
+
+This design allows FastVideo to efficiently utilize multiple GPUs while providing a simple, unified interface for model execution.
+
+## Platforms
+
+The `fastvideo/platforms/` directory provides hardware platform abstractions that enable FastVideo to run efficiently on different hardware configurations:
+
+### Platform Abstraction
+
+FastVideo's platform abstraction layer enables:
+- **Hardware Detection**: Automatic detection of available hardware
+- **Backend Selection**: Appropriate selection of compute kernels
+- **Memory Management**: Efficient utilization of hardware-specific memory features
+
+The primary components include:
+- **Platform Interface**: Defines the common API for all platform implementations
+- **CUDA Platform**: Optimized implementation for NVIDIA GPUs
+- **Backend Enum**: Used throughout the codebase for feature selection
+
+Usage example:
+
+```python
+from fastvideo.platforms import current_platform, _Backend
+
+# Check hardware capabilities
+if current_platform.supports_backend(_Backend.FLASH_ATTN):
+    # Use FlashAttention implementation
+else:
+    # Fall back to standard implementation
 ```

-How this maps to FastVideo:
+The platform system is designed to be extensible for future hardware targets.

- `WanPipeline` -> `fastvideo/pipelines/basic/wan/wan_pipeline.py`
- `WanTransformer3DModel` -> `fastvideo/models/dits/wanvideo.py`
- `AutoencoderKLWan` -> `fastvideo/models/vaes/wanvae.py`
- `UMT5EncoderModel` -> `fastvideo/models/encoders/t5.py`
- `T5TokenizerFast` -> loaded via HF in `fastvideo/models/loader/`
- `UniPCMultistepScheduler` -> loaded via Diffusers scheduler utilities
- Pipeline defaults -> `fastvideo/configs/pipelines/wan.py`
- Sampling defaults -> `fastvideo/configs/sample/wan.py`
+## Logger
+See [PR](https://github.com/hao-ai-lab/FastVideo/pull/356)

-## Pipeline system
+*TODO*: (help wanted) Add an environment variable that disables process-aware logging.

- `fastvideo/pipelines/basic/*` contains end-to-end pipelines for each model
-  family.
- `fastvideo/pipelines/stages/*` contains reusable, testable stages.
- Pipelines subclass `ComposedPipelineBase` and declare required components via
-  `_required_config_modules`.
- `ForwardBatch` (in `fastvideo/pipelines/pipeline_batch_info.py`) carries
-  prompts, latents, timesteps, and intermediate state across stages.
+## Contributing to FastVideo

-## Model components
+If you're a new contributor, here are some common areas to explore:

- DiT models: `fastvideo/models/dits/`
- VAEs: `fastvideo/models/vaes/`
- Text/image encoders: `fastvideo/models/encoders/`
- Schedulers: `fastvideo/models/schedulers/`
- Upsamplers: `fastvideo/models/upsamplers/`
- Optional audio models: `fastvideo/models/audio/`
+1. **Adding a new model**: Implement new model types in the appropriate subdirectory of `fastvideo/models/`
+2. **Optimizing performance**: Look at attention implementations or memory management
+3. **Adding a new pipeline**: Create a new pipeline subclass in `fastvideo/pipelines/`
+4. **Hardware support**: Extend the `platforms` module for new hardware targets

-## Attention and distributed execution
-
- Attention backends live in `fastvideo/attention/` and can be selected via
-  `FASTVIDEO_ATTENTION_BACKEND`.
- `LocalAttention` is used for cross-attention and most attention layers.
- `DistributedAttention` is used for full-sequence self-attention in the DiT.
- Tensor-parallel layers live in `fastvideo/layers/`.
- Sequence/tensor parallel utilities live in `fastvideo/distributed/`.
-
-## Related docs
-
- [Contributing overview](../contributing/overview.md)
- [Coding agents workflow](../contributing/coding_agents.md)
- [Testing guide](../contributing/testing.md)
+When adding code, follow these practices:
+- Use type hints for better code readability
+- Add appropriate docstrings
+- Maintain the separation between model components and execution logic
+- Follow existing patterns for distributed processing
@@ -13,7 +13,7 @@ We provide two distilled models:
 Both models are trained on **61×448×832** resolution but support generating videos with **any resolution** (1.3B  model mainly support 480P, 14B model support 480P and 720P, quality may degrade for different resolutions).

 ## ⚙️ Inference
-First install [VSA](../attention/vsa/index.md). Set `MODEL_BASE` to your own model path and run:
+First install [VSA](https://hao-ai-lab.github.io/FastVideo/video_sparse_attention/installation). Set `MODEL_BASE` to your own model path and run:

 ```bash
 bash scripts/inference/v1_inference_wan_dmd.sh
@@ -11,13 +11,15 @@ FastVideo supports the following hardware platforms:
 ### Using pip

 ```bash
-# Create and activate a new conda environment
-conda create -n fastvideo python=3.12
-conda activate fastvideo
-
 pip install fastvideo
 ```

+### Using conda
+
+```bash
+conda install -c conda-forge fastvideo
+```
+
 ### From source

 ```bash
@@ -26,12 +28,6 @@ cd FastVideo
 pip install -e .
 ```

-Also optionally install flash-attn:
-
-```bash
-pip install flash-attn --no-build-isolation
-```
-
 ## Hardware Requirements

 - **NVIDIA GPUs**: CUDA 11.8+ with compute capability 7.0+
@@ -42,4 +38,4 @@ pip install flash-attn --no-build-isolation

 - [Quick Start Guide](quick_start.md) - Get started with your first video generation
 - [Configuration](../inference/configuration.md) - Learn about configuration options
- [Examples](../inference/examples/examples_inference_index.md) - Explore example scripts and notebooks
+- [Examples](../inference/examples/) - Explore example scripts and notebooks
@@ -84,12 +84,12 @@ pip install flash-attn --no-build-isolation

 ## Set up using Docker
 We also have prebuilt docker images with FastVideo dependencies pre-installed:
-[Docker Images](../../contributing/developer_env/docker.md)
+[Docker Images](#docker)

 ## Development Environment Setup

 If you're planning to contribute to FastVideo please see the following page:
-[Contributor Guide](../../contributing/overview.md)
+[Contributor Guide](#developer-overview)

 ## Hardware Requirements

@@ -78,7 +78,7 @@ uv pip install -e .
 ## Development Environment Setup

 If you're planning to contribute to FastVideo please see the following page:
-[Contributor Guide](../../contributing/overview.md)
+[Contributor Guide](#developer-overview)

 ## Hardware Requirements

@@ -15,12 +15,6 @@ conda activate fastvideo
 pip install fastvideo
 ```

-Also optionally install flash-attn:
-
-```bash
-pip install flash-attn --no-build-isolation
-```
-
 ## Basic Usage

 ### Text-to-Video Generation
@@ -81,3 +75,4 @@ if __name__ == '__main__':
 - [Configuration](../inference/configuration.md) - Learn about configuration options
 - [Examples](../inference/examples/) - Explore more examples
 - [Optimizations](../inference/optimizations.md) - Performance optimization tips
+- [Low VRAM Inference](../inference/low_vram_inference.md) - Memory-saving settings (CPU offload, sharded loading, etc.)
@@ -45,7 +45,6 @@ FastVideo uses the Hugging Face Diffusers format for model organization:
 ### Implementing Modules

 Place new modules in the appropriate directories:
-
 - Encoders: `fastvideo/models/encoders/`
 - VAEs: `fastvideo/models/vaes/`
 - Transformer models: `fastvideo/models/dits/`
@@ -54,15 +53,12 @@ Place new modules in the appropriate directories:
 ### Adapting Model Layers

 #### Layer Replacements
-
 Replace standard PyTorch layers with FastVideo optimized versions:
-
 - nn.LayerNorm → fastvideo.layers.layernorm.RMSNorm
 - Embedding layers → fastvideo.layers.vocab_parallel_embedding modules
 - Activation functions → versions from fastvideo.layers.activation

 #### Distributed Linear Layers
-
 Use appropriate parallel layers for distribution:

 ```python
@@ -95,7 +91,6 @@ self.out_proj = RowParallelLinear(
 ```

 ### Attention Layers
-
 Replace standard attention with FastVideo's optimized attention:

 ```python
@@ -131,41 +126,17 @@ self.attn = DistributedAttention(

 ### Registering Models

-Register implemented modules for auto‑discovery by adding `EntryClass` in each
-model module (the registry scans for it):
+Register implemented modules in the model registry:

 ```python
-# In fastvideo/models/dits/your_module.py
-class YourTransformerModel(...):
-    ...
+# In fastvideo/models/registry.py
+_TEXT_TO_VIDEO_DIT_MODELS = {
+    "YourTransformerModel": ("dits", "yourmodule", "YourTransformerClass"),
+}

-# Entry point for model registry
-EntryClass = YourTransformerModel
-```
-
-```python
-# In fastvideo/models/vaes/your_vae.py
-class YourVAEModel(...):
-    ...
-
-# Entry point for model registry
-EntryClass = YourVAEModel
-```
-
-Register pipeline config + sampling defaults in the unified registry:
-
-```python
-# In fastvideo/registry.py
-register_configs(
-    sampling_param_cls=YourSamplingParam,
-    pipeline_config_cls=YourPipelineConfig,
-    hf_model_paths=[
-        "org/your-model-id",
-    ],
-    model_detectors=[
-        lambda path: "your-model" in path.lower(),
-    ],
-)
+_VAE_MODELS = {
+    "YourVAEModel": ("vaes", "yourvae", "YourVAEClass"),
+}
 ```

 ## Step 2: Directory Structure
@@ -333,7 +304,6 @@ EntryClass = [MyCustomPipeline, MyOtherPipeline]
 ```

 The registry will automatically:
-
 1. Scan all packages under `fastvideo/pipelines/`
 2. Look for `EntryClass` variables
 3. Register pipelines using their class names as identifiers
@@ -1,7 +1,7 @@
 # FastVideo CLI Inference

 The FastVideo CLI provides a quick way to access the FastVideo inference pipeline for video generation. For more advanced usage,
-see the Python interface [here](examples/basic.md).
+see the Python interface [here](https://hao-ai-lab.github.io/FastVideo/inference/examples/basic.html).

 ## Basic Usage

@@ -74,4 +74,4 @@ if __name__ == '__main__':

 ## Performance Optimization

-For configuring optimizations, please see our [optimizations guide](optimizations.md)
+For configuring optimizations, please see our [optimizations guide](#inference-optimizations)
@@ -3,7 +3,6 @@
 This page contains step-by-step instructions to get you quickly started with video generation using FastVideo.

 ## Requirements
-
 - **OS**: Linux (Tested on Ubuntu 22.04+)
 - **Python**: 3.10-3.12
 - **CUDA**: 12.8
@@ -22,10 +21,9 @@ conda activate fastvideo
 pip install fastvideo
 ```

-For advanced installation options, see the [Installation Guide](../getting_started/installation.md).
+For advanced installation options, see the [Installation Guide](installation.md).

 ## Generating Your First Video
-
 Here's a minimal example to generate a video using the default settings. Create a file called `example.py` with the following code:

 ```python
@@ -62,10 +60,9 @@ python example.py
 The generated video will be saved in the current directory under `my_videos/`  

 More inference example scripts can be found in `scripts/inference/`
-
 ## Available Models

-Please see the [support matrix](support_matrix.md) for the list of supported models and their available optimizations.
+Please see the [support matrix](#support-matrix) for the list of supported models and their available optimizations.

 ## Image-to-Video Generation

@@ -99,28 +96,20 @@ if __name__ == '__main__':
 Common issues and their solutions:

 ### Out of Memory Errors
-
 If you encounter CUDA out of memory errors:
-
 - Reduce `num_frames` or video resolution
- Enable memory optimization with `enable_model_cpu_offload`
+- Enable memory optimization with CPU-offload and sharded loading flags (see [Low VRAM Inference](low_vram_inference.md))
 - Try a smaller model or use distilled versions
 - Use `num_gpus` > 1 if multiple GPUs are available
- Try enabling FSDP inference with `use_fsdp_inference=True` (may slow down generation)
- Try enabling DiT layerwise offload with `dit_layerwise_offload=True` (now only a few models support this, but may introduce less overhead than FSDP)

 ### Slow Generation
-
 To speed up generation:
-
 - Reduce `num_inference_steps` (20-30 is usually sufficient)
 - Use half precision (`fp16`) for the VAE
 - Use multiple GPUs if available

 ### Unexpected Results
-
 If the generated video doesn't match your prompt:
-
 - Try increasing `guidance_scale` (7.0-9.0 works well)
 - Make your prompt more detailed and specific
 - Experiment with different random seeds
@@ -128,8 +117,8 @@ If the generated video doesn't match your prompt:

 ## Next Steps

- Learn about [Advanced Inference Configurations](configuration.md)
- Learn about using [Optimizations](optimizations.md)
- See [Examples](examples/examples_inference_index.md) for more usage scenarios
+- Learn about [Advanced Inference Configurations](#inference-configuration)
+- Learn about using [Optimizations](#inference-optimizations)
+- See [Examples](../examples/examples_inference_index.md) for more usage scenarios
 - Join our [Community Discord](https://discord.gg/JA7cksDz86).
 - Join our [Community Slack](https://join.slack.com/t/fastvideo/shared_invite/zt-38u6p1jqe-yDI1QJOCEnbtkLoaI5bjZQ).
@@ -1,140 +0,0 @@
-# Offloading
-
-This page describes how to use offloading techniques for inference to reduce GPU memory usage while maintaining acceptable performance.
-
-## Default Behavior
-
-```python
-dit_cpu_offload: bool = True
-use_fsdp_inference: bool = False
-dit_layerwise_offload: bool = True
-text_encoder_cpu_offload: bool = True
-image_encoder_cpu_offload: bool = True
-vae_cpu_offload: bool = True
-pin_cpu_memory: bool = True
-```
-
-## Behavior Explanation
-
-!!! note
-    For CLI usage, replace underscores (`_`) with hyphens (`-`).
-
-### `use_fsdp_inference`
-
-Enables [FSDP](https://docs.pytorch.org/tutorials/intermediate/FSDP_tutorial.html) for inference. The model weights are sharded across multiple GPUs to reduce memory usage per GPU, and weights are broadcast to all GPUs layer by layer during inference.
-
-#### Performance Impact
-
-FSDP inference introduces negligible performance overhead due to weight prefetching. Performance overhead may be visible when GPU interconnect is slow (e.g., multiple consumer-level GPUs connected by slow PCIe without GPU P2P support).
-
-#### Usage Recommendation
-
-We recommend enabling this option when multiple GPUs are available.
-
-### `dit_cpu_offload`
-
-Enables CPU offloading for FSDP inference. When enabled, the model weights are offloaded to CPU memory, and the weight of each layer is moved to GPU memory only when that layer is being computed.
-
-#### Performance Impact
-
-The PyTorch FSDP implementation does not overlap computation and data transfer perfectly for inference, so enabling this option will harm performance.
-
-#### Usage Recommendation
-
-This option only takes effect when FSDP is enabled. For single GPU usage, we recommend using `dit_layerwise_offload` instead.
-
-### `dit_layerwise_offload`
-
-This option is similar to `dit_cpu_offload`, but with two key differences:
-
-1. It overlaps computation and PCIe data transfer
-2. It only works for single GPU inference
-
-#### Performance Impact
-
-This option introduces negligible performance overhead.
-
-#### Usage Recommendation
-
-We recommend enabling this option for single GPU usage. This option is not compatible with FSDP.
-
-### `text_encoder_cpu_offload`
-
-When enabled, the text encoder model weights are offloaded to CPU memory, and text encoding is computed on CPU.
-
-#### Performance Impact
-
-This option significantly slows down text encoding computation, but text encoding is usually not the bottleneck.
-
-#### Usage Recommendation
-
-We recommend enabling this option only when OOM happens.
-
-### `image_encoder_cpu_offload` and `vae_cpu_offload`
-
-When enabled, the weights are stored in CPU memory and moved to GPU memory when the corresponding module is being computed. After computation, the weights are moved back to CPU memory.
-
-#### Performance Impact
-
-These options introduce performance overhead due to PCIe data transfer.
-
-#### Usage Recommendation
-
-We recommend enabling these options when OOM happens.
-
-## General Recommendations
-
-### Single GPU Inference
-
-We recommend enabling `dit_layerwise_offload`. If OOM happens, also enable `image_encoder_cpu_offload` and `vae_cpu_offload`. If OOM still happens, consider enabling `text_encoder_cpu_offload`.
-
-### Multi-GPU Inference
-
-We recommend enabling `use_fsdp_inference` and disabling both `dit_layerwise_offload` and `dit_cpu_offload`. If OOM happens, consider enabling `text_encoder_cpu_offload`, `image_encoder_cpu_offload`, and `vae_cpu_offload`. If OOM still happens, consider enabling `dit_cpu_offload`.
-
-## Examples
-
-### Single GPU with Layerwise Offloading
-
-```python
-from fastvideo import VideoGenerator
-
-generator = VideoGenerator.from_pretrained(
-    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
-    num_gpus=1,
-    # Recommended for single GPU
-    dit_layerwise_offload=True,
-    # Enable if OOM happens
-    vae_cpu_offload=True,
-    image_encoder_cpu_offload=True,
-    text_encoder_cpu_offload=True,
-    # Speeds up CPU-GPU transfer
-    pin_cpu_memory=True,
-)
-
-prompt = "A curious raccoon peers through a vibrant field of yellow sunflowers."
-video = generator.generate_video(prompt, output_path="output/", save_video=True)
-```
-
-### Multi-GPU with FSDP
-
-```python
-from fastvideo import VideoGenerator
-
-generator = VideoGenerator.from_pretrained(
-    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
-    num_gpus=2,
-    # Recommended for multi-GPU
-    use_fsdp_inference=True,
-    dit_layerwise_offload=False,
-    dit_cpu_offload=False,
-    # Enable if OOM happens
-    vae_cpu_offload=True,
-    image_encoder_cpu_offload=True,
-    text_encoder_cpu_offload=True,
-    pin_cpu_memory=True,
-)
-
-prompt = "A majestic lion strides across the golden savanna."
-video = generator.generate_video(prompt, output_path="output/", save_video=True)
-```
@@ -7,13 +7,13 @@ This page describes the various options for speeding up generation times in Fast

 - Optimized Attention Backends

-  - [Flash Attention](#flash-attention)
-  - [Sliding Tile Attention](#sliding-tile-attention)
-  - [Sage Attention](#sage-attention)
-  - [Sage Attention 3](#sage-attention-3)
+  - [Flash Attention](#optimizations-flash)
+  - [Sliding Tile Attention](#optimizations-sta)
+  - [Sage Attention](#optimizations-sage)
+  - [Sage Attention 3](#optimizations-sage3)

 - Caching Techniques
-  - [TeaCache](#teacache)
+  - [TeaCache](#optimizations-teacache)

 ## Attention Backends

@@ -74,7 +74,7 @@ python setup.py install
 pip install st_attn==0.0.4
 ```

-Please see [this page](../attention/sta/index.md) for more installation instructions.
+Please see [this page](#sta-installation) for more installation instructions.

 ### Video Sparse Attention

@@ -85,7 +85,7 @@ git submodule update --init --recursive
 python setup_vsa.py install
 ```

-Please see [this page](../attention/vsa/index.md) for more installation instructions.
+Please see [this page](#vsa-installation) for more installation instructions.

 ### Sage Attention

@@ -103,7 +103,7 @@ python setup.py install  # or pip install -e .

 **`SAGE_ATTN_THREE`**

-[SageAttention 3](https://github.com/thu-ml/SageAttention/tree/main/sageattention3_blackwell) is an advanced attention mechanism that leverages FP4 quantization and Blackwell GPU Tensor Cores for significant performance improvements.
+[SageAttention 3](https://huggingface.co/jt-zhang/SageAttention3) is an advanced attention mechanism that leverages FP4 quantization and Blackwell GPU Tensor Cores for significant performance improvements.

 #### Hardware Requirements

@@ -113,7 +113,11 @@ python setup.py install  # or pip install -e .

 Note that Sage Attention 3 requires `python>=3.13`, `torch>=2.8.0`, `CUDA >=12.8`. If you are using `uv` and using `torch==2.8.0` make sure that `sentencepiece==0.2.1` in the pyproject.toml file.

-To use Sage Attention 3 in FastVideo, follow the `README.md` in the linked repository to install the package from source.
+To use Sage Attention 3 in FastVideo, first get access to the SageAttention3 code, then move `sageattn/` and `setup.py` to the directory `fastvideo/attention/backends`, then install from using:
+
+```bash
+python setup.py install
+```

 ## Teacache

@@ -40,26 +40,20 @@ The `HuggingFace Model ID` can be directly pass to `from_pretrained()` methods a
  }
 </style>

-| Model Name | HuggingFace Model ID | Resolutions | TeaCache | Sliding Tile Attn | Sage Attn | VSA | BSA |
-|------------|---------------------|-------------|----------|-------------------|-----------|-----|-----|
-| FastWan2.1 T2V 1.3B | `FastVideo/FastWan2.1-T2V-1.3B-Diffusers` | 480P | ⭕ | ⭕ | ⭕ | ✅ | ⭕ |
-| FastWan2.2 TI2V 5B Full Attn* | `FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers` | 720P | ⭕ | ⭕ | ⭕ | ✅ | ⭕ |
-| Wan2.2 TI2V 5B | `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | 720P | ⭕ | ⭕ | ✅ | ⭕ | ⭕ |
-| Wan2.2 T2V A14B | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | 480P<br>720P | ❌ | ❌ | ✅ | ⭕ | ⭕ |
-| Wan2.2 I2V A14B | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | 480P<br>720P | ❌ | ❌ | ✅ | ⭕ | ⭕ |
-| HunyuanVideo | `hunyuanvideo-community/HunyuanVideo` | 720px1280p<br>544px960p | ❌ | ✅ | ✅ | ⭕ | ⭕ |
-| FastHunyuan | `FastVideo/FastHunyuan-diffusers` | 720px1280p<br>544px960p | ❌ | ✅ | ✅ | ⭕ | ⭕ |
-| Wan2.1 T2V 1.3B | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers` | 480P | ✅ | ✅* | ✅ | ⭕ | ⭕ |
-| Wan2.1 T2V 14B | `Wan-AI/Wan2.1-T2V-14B-Diffusers` | 480P, 720P | ✅ | ✅* | ✅ | ⭕ | ⭕ |
-| Wan2.1 I2V 480P | `Wan-AI/Wan2.1-I2V-14B-480P-Diffusers` | 480P | ✅ | ✅* | ✅ | ⭕ | ⭕ |
-| Wan2.1 I2V 720P | `Wan-AI/Wan2.1-I2V-14B-720P-Diffusers` | 720P | ✅ | ✅ | ✅ | ⭕ | ⭕ |
-| StepVideo T2V | `FastVideo/stepvideo-t2v-diffusers` | 768px768px204f<br>544px992px204f<br>544px992px136f | ❌ | ❌ | ✅ | ⭕ | ⭕ |
-| TurboWan2.1 T2V 1.3B | `loayrashid/TurboWan2.1-T2V-1.3B-Diffusers` | 480P | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
-| TurboWan2.1 T2V 14B | `loayrashid/TurboWan2.1-T2V-14B-Diffusers` | 480P, 720P | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
-| LongCat T2V 13.6B | See note** | 480P<br>720P | ❌ | ❌ | ❌ | ⭕ | ✅ |
-| Matrix Game 2.0 Base | `FastVideo/Matrix-Game-2.0-Base-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
-| Matrix Game 2.0 GTA | `FastVideo/Matrix-Game-2.0-GTA-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
-| Matrix Game 2.0 TempleRun | `FastVideo/Matrix-Game-2.0-TempleRun-Diffusers` | 352x640 | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ |
+| Model Name | HuggingFace Model ID | Resolutions | TeaCache | Sliding Tile Attn | Sage Attn | VSA |
+|------------|---------------------|-------------|----------|-------------------|-----------|-----|
+| FastWan2.1 T2V 1.3B | `FastVideo/FastWan2.1-T2V-1.3B-Diffusers` | 480P | ⭕ | ⭕ | ⭕ | ✅ |
+| FastWan2.2 TI2V 5B Full Attn* | `FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers` | 720P | ⭕ | ⭕ | ⭕ | ✅ |
+| Wan2.2 TI2V 5B | `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | 720P | ⭕ | ⭕ | ✅ | ⭕ |
+| Wan2.2 T2V A14B | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | 480P<br>720P | ❌ | ❌ | ✅ | ⭕ |
+| Wan2.2 I2V A14B | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | 480P<br>720P | ❌ | ❌ | ✅ | ⭕ |
+| HunyuanVideo | `hunyuanvideo-community/HunyuanVideo` | 720px1280p<br>544px960p | ❌ | ✅ | ✅ | ⭕ |
+| FastHunyuan | `FastVideo/FastHunyuan-diffusers` | 720px1280p<br>544px960p | ❌ | ✅ | ✅ | ⭕ |
+| Wan2.1 T2V 1.3B | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers` | 480P | ✅ | ✅* | ✅ | ⭕ |
+| Wan2.1 T2V 14B | `Wan-AI/Wan2.1-T2V-14B-Diffusers` | 480P, 720P | ✅ | ✅* | ✅ | ⭕ |
+| Wan2.1 I2V 480P | `Wan-AI/Wan2.1-I2V-14B-480P-Diffusers` | 480P | ✅ | ✅* | ✅ | ⭕ |
+| Wan2.1 I2V 720P | `Wan-AI/Wan2.1-I2V-14B-720P-Diffusers` | 720P | ✅ | ✅ | ✅ | ⭕ |
+| StepVideo T2V | `FastVideo/stepvideo-t2v-diffusers` | 768px768px204f<br>544px992px204f<br>544px992px136f | ❌ | ❌ | ✅ | ⭕ |

 **Note**: Wan2.2 TI2V 5B has some quality issues when performing I2V generation. We are working on fixing this issue.

@@ -70,13 +64,3 @@ The `HuggingFace Model ID` can be directly pass to `from_pretrained()` methods a

 ### Sliding Tile Attention
 - Currently only Hopper GPUs (H100s) are supported.
-
-### TurboWan2.1 (TurboDiffusion)
- Uses TurboDiffusionPipeline with RCM scheduler for 1-4 step generation
- Requires SLA attention backend: `export FASTVIDEO_ATTENTION_BACKEND=SLA_ATTN`
- Uses `guidance_scale=1.0` (no classifier-free guidance)
-
-### Matrix Game 2.0
- Image-to-video game world models with keyboard/mouse control input
- Three variants available: Base (universal), GTA, and TempleRun
- Each variant has different keyboard dimensions for control inputs
@@ -1,130 +1,45 @@
-# 🧱 Data Preprocessing

-To save GPU memory during training, FastVideo precomputes text embeddings and VAE latents. This eliminates the need to load the text encoder and VAE during training.
+# 🧱 Data Preprocess

-## Quick Start
+To save GPU memory, we precompute text embeddings and VAE latents to eliminate the need to load the text encoder and VAE during training.

-Download the sample dataset and run preprocessing:
+We provide a sample dataset to help you get started. Download the source media using the following command:

 ```bash
-# Download the crush-smol dataset
-python scripts/huggingface/download_hf.py \
-    --repo_id "wlsaidhi/crush-smol-merged" \
-    --local_dir "data/crush-smol" \
-    --repo_type "dataset"
-
-# Run preprocessing
-bash examples/training/finetune/wan_t2v_1.3B/crush_smol/preprocess_wan_data_t2v_new.sh
+python scripts/huggingface/download_hf.py --repo_id=FastVideo/mini_i2v_dataset --local_dir=data/mini_i2v_dataset --repo_type=dataset
 ```

-## Preprocessing Pipeline
+The folder `crush-smol_raw/` contains raw videos and captions for testing preprocessing, while `crush-smol_preprocessed/` contains latents prepared for testing training.

-The new preprocessing pipeline supports multiple dataset formats and video loaders:
-
-```bash
-GPU_NUM=2
-MODEL_PATH="Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
-DATASET_PATH="data/crush-smol/"
-OUTPUT_DIR="data/crush-smol_processed_t2v/"
-
-torchrun --nproc_per_node=$GPU_NUM \
-    -m fastvideo.pipelines.preprocess.v1_preprocessing_new \
-    --model_path $MODEL_PATH \
-    --mode preprocess \
-    --workload_type t2v \
-    --preprocess.video_loader_type torchvision \
-    --preprocess.dataset_type merged \
-    --preprocess.dataset_path $DATASET_PATH \
-    --preprocess.dataset_output_dir $OUTPUT_DIR \
-    --preprocess.preprocess_video_batch_size 2 \
-    --preprocess.dataloader_num_workers 0 \
-    --preprocess.max_height 480 \
-    --preprocess.max_width 832 \
-    --preprocess.num_frames 77 \
-    --preprocess.train_fps 16 \
-    --preprocess.samples_per_file 8 \
-    --preprocess.flush_frequency 8 \
-    --preprocess.video_length_tolerance_range 5
-```
-
-### Key Parameters
-
-| Parameter | Description |
-|-----------|-------------|
-| `--workload_type` | Task type: `t2v` (text-to-video) or `i2v` (image-to-video) |
-| `--preprocess.dataset_type` | Input format: `hf` (HuggingFace) or `merged` (local folder) |
-| `--preprocess.dataset_path` | Path to dataset (HF repo ID or local folder) |
-| `--preprocess.dataset_output_dir` | Output directory for Parquet files |
-| `--preprocess.video_loader_type` | Video decoder: `torchcodec` or `torchvision` |
-| `--preprocess.max_height` / `max_width` | Target resolution for videos |
-| `--preprocess.num_frames` | Number of frames to extract per video |
-| `--preprocess.train_fps` | Target FPS for frame extraction |
-
-## Dataset Formats
-
-### Merged Dataset (Local Folder)
-
-Structure your dataset as follows:
+To preprocess the dataset for fine-tuning or distillation, run:

 ```
-your_dataset/
-├── videos/
-│   ├── video_001.mp4
-│   ├── video_002.mp4
-│   └── ...
-└── videos2caption.json
+bash scripts/preprocess/v1_preprocess_wan_data_t2v # for wan
 ```

-The `videos2caption.json` maps video filenames to captions:
+## Process your own dataset

-```json
-[
-  {"path": "video_001.mp4", "cap": "A cat playing with yarn..."},
-  {"path": "video_002.mp4", "cap": "Ocean waves at sunset..."}
-]
-```
-
-### HuggingFace Dataset
-
-Use `--preprocess.dataset_type hf` and point `--preprocess.dataset_path` to a HuggingFace dataset with `video` and `caption` columns.
-
-## Creating Your Own Dataset
-
-If you have raw videos and captions in separate files, generate the `videos2caption.json`:
-
-```bash
-python scripts/dataset_preparation/prepare_json_file.py \
-    --data_folder path/to/your_raw_data/ \
-    --output path/to/output_folder
-```
-
-Your raw data folder should contain:
+If you wish to create your own dataset for finetuning or distillation, please refer `mini_i2v_dataset/crush-smol_raw/` to structure you video dataset in the following format:

 ```
-your_raw_data/
+path_to_your_dataset_folder/
 ├── videos/
 │   ├── 0.mp4
 │   ├── 1.mp4
-│   └── ...
-├── videos.txt    # list of video filenames
-└── prompt.txt    # corresponding captions (one per line)
+├── videos.txt
+└── prompt.txt
 ```

-## Output Format
+To generate the `videos2caption.json` and `merge.txt`, run

-Preprocessing outputs Parquet files in the `combined_parquet_dataset/` subdirectory containing:
+``` python
+python scripts/dataset_preparation/prepare_json_file.py --data_folder mini_i2v_dataset/crush-smol_raw/ --output your_output_folder
+```

- `vae_latent_bytes` — VAE-encoded video latent
- `text_embedding_bytes` — text encoder output
- `clip_feature_bytes` — CLIP image features (I2V only)
- `first_frame_latent_bytes` — first frame latent (I2V only)
- Metadata: shapes, dtypes, and sample identifiers
+Adjust the `DATA_MERGE_PATH` and `OUTPUT_DIR` in `scripts/preprocess/v1_preprocess_****.sh` accordingly and run:

-## Examples
+```
+bash scripts/preprocess/v1_preprocess_****.sh
+```

-See ready-to-run preprocessing scripts in the training examples:
-
- **T2V**: `examples/training/finetune/wan_t2v_1.3B/crush_smol/preprocess_wan_data_t2v_new.sh`
- **I2V**: `examples/training/finetune/wan_i2v_14B_480p/crush_smol/preprocess_wan_data_i2v_new.sh`
-
-**→ [Browse all training examples](examples/examples_training_index.md)**
+The preprocessed data will be put into the `OUTPUT_DIR` and the `videos2caption.json` can be used in finetune and distill scripts.
@@ -1,176 +1,78 @@
-# 🧠 Finetuning

-This guide covers finetuning video diffusion models with FastVideo, including full finetuning and LoRA.
-
-## Training Arguments
-
-FastVideo training scripts use several argument groups:
-
-### Training Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `--max_train_steps` | Total training steps |
-| `--train_batch_size` | Batch size per GPU |
-| `--gradient_accumulation_steps` | Steps to accumulate before optimizer update |
-| `--num_latent_t` | Temporal latent dimension (reduce to save memory) |
-| `--num_height` / `--num_width` | Video resolution |
-| `--num_frames` | Number of frames per video |
-| `--output_dir` | Directory for checkpoints |
-
-### Parallelism Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `--num_gpus` | Total number of GPUs |
-| `--sp_size` | Sequence parallel size (increase to reduce memory per GPU) |
-| `--tp_size` | Tensor parallel size |
-| `--hsdp_replicate_dim` | HSDP replication dimension |
-| `--hsdp_shard_dim` | HSDP sharding dimension |
-
-### Optimizer Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `--learning_rate` | Base learning rate |
-| `--mixed_precision` | Precision mode (`bf16` recommended) |
-| `--weight_decay` | Weight decay for regularization |
-| `--max_grad_norm` | Gradient clipping threshold |
-
-### Validation Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `--log_validation` | Enable validation logging |
-| `--validation_dataset_file` | JSON file with validation prompts |
-| `--validation_steps` | Run validation every N steps |
-| `--validation_sampling_steps` | Inference steps for validation |
-| `--validation_guidance_scale` | CFG scale for validation |
-
-## Full Finetuning
-
-Full finetuning updates all model weights. This provides the best quality but requires more GPU memory.
+# 🧠 Finetune
+## ⚡ Full Finetune
+Ensure your data is prepared and preprocessed in the format specified in [data_preprocess.md](#v0-data-preprocess). For convenience, we also provide a mochi preprocessed Black Myth Wukong data that can be downloaded directly:

 ```bash
-# Example: Wan2.1 T2V 1.3B full finetune (4 GPUs)
-bash examples/training/finetune/wan_t2v_1.3B/crush_smol/finetune_t2v.sh
+python scripts/huggingface/download_hf.py --repo_id=FastVideo/Mochi-Black-Myth --local_dir=data/Mochi-Black-Myth --repo_type=dataset
 ```

-**Typical settings:**
+Download the original model weights as specified in the [Distillation Section](../distillation/dmd.md):

- Learning rate: `1e-5` to `5e-5`
- Gradient checkpointing: `--enable_gradient_checkpointing_type "full"`
- Memory scaling: Increase `--sp_size` or reduce `--num_latent_t` to fit in memory
+Then you can run the finetune with:

-## LoRA Finetuning
+```
+bash scripts/finetune/finetune_mochi.sh # for mochi
+```

-LoRA (Low-Rank Adaptation) trains lightweight adapters while keeping the base model frozen. This significantly reduces memory usage and training time.
-
-### LoRA-Specific Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `--lora_training True` | Enable LoRA mode |
-| `--lora_rank` | Rank of LoRA adapters (16, 32, 64, 128) |
-
-### Learning Rate for LoRA
-
-**Important:** LoRA typically requires a **10–20× higher learning rate** than full finetuning because only the low-rank adapters are being trained while the base model is frozen.
-
-| Training Mode | Recommended Learning Rate |
-|---------------|---------------------------|
-| Full finetune | `1e-5` to `5e-5` |
-| LoRA | `1e-4` to `2e-4` |
-
-### Example LoRA Training
+**Note that for finetuning, we did not tune the hyperparameters in the provided script.**
+## ⚡ Finetune with VSA
+Follow [data_preprocess.md](#v0-data-preprocess) to get parquet files for preproccessed latent, and then run:

 ```bash
-# Example: Wan2.1 T2V 1.3B LoRA finetune (1 GPU)
-bash examples/training/finetune/wan_t2v_1.3B/crush_smol/finetune_t2v_lora.sh
+bash scripts/finetune/finetune_v1_VSA.sh
 ```

-Key differences from full finetune:
+## ⚡ Lora Finetune

- Add `--lora_training True --lora_rank 32`
- Use higher learning rate (10–20× full finetune)
- Can run on fewer GPUs (even single GPU)
- Outputs adapter weights instead of full model
-
-## LoRA Extraction and Merging
-
-FastVideo provides tools to extract LoRA adapters from finetuned models and merge them back.
-
-### Extract LoRA Adapter
-
-Extract a LoRA adapter by comparing a finetuned model to its base:
+Hunyuan supports Lora fine-tuning of videos up to 720p. Demos and prompts of Black-Myth-Wukong can be found in [here](https://huggingface.co/FastVideo/Hunyuan-Black-Myth-Wukong-lora-weight). You can download the Lora weight through:

 ```bash
-python scripts/lora_extraction/extract_lora.py \
-  --base Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
-  --ft path/to/your/finetuned_model \
-  --out adapter_r32.safetensors \
-  --rank 32
+python scripts/huggingface/download_hf.py --repo_id=FastVideo/Hunyuan-Black-Myth-Wukong-lora-weight --local_dir=data/Hunyuan-Black-Myth-Wukong-lora-weight --repo_type=model
 ```

-| Argument | Description |
-|----------|-------------|
-| `--base` | Base model (HuggingFace ID or local path) |
-| `--ft` | Finetuned model path |
-| `--out` | Output adapter file (.safetensors) |
-| `--rank` | LoRA rank (16, 32, 64, 128) |
-| `--full-rank` | Extract full-rank adapter (optional) |
+### Minimum Hardware Requirement
+- 40 GB GPU memory each for 2 GPUs with lora.
+- 30 GB GPU memory each for 2 GPUs with CPU offload and lora.

-### Merge LoRA Adapter
+Currently, both Mochi and Hunyuan models support Lora finetuning through diffusers. To generate personalized videos from your own dataset, you'll need to follow three main steps: dataset preparation, finetuning, and inference.

-Merge an adapter back into a base model:
+### Dataset Preparation
+We provide scripts to better help you get started to train on your own characters!
+You can run this to organize your dataset to get the videos2caption.json before preprocess. Specify your video folder and corresponding caption folder (caption files should be .txt files and have the same name with its video):
+
+```
+python scripts/dataset_preparation/prepare_json_file.py --video_dir data/input_videos/ --prompt_dir data/captions/ --output_path data/output_folder/videos2caption.json --verbose
+```
+
+Also, we provide script to resize your videos:
+
+```
+python scripts/data_preprocess/resize_videos.py
+```
+
+### Finetuning
+After basic dataset preparation and preprocess, you can start to finetune your model using Lora:
+
+```
+bash scripts/finetune/finetune_hunyuan_hf_lora.sh
+```
+
+### Inference
+For inference with Lora checkpoint, you can run the following scripts with additional parameter `--lora_checkpoint_dir`:
+
+```
+bash scripts/inference/inference_hunyuan_hf.sh
+```
+
+**We also provide scripts for Mochi in the same directory.**
+
+### Finetune with Both Image and Video
+Our codebase support finetuning with both image and video.

 ```bash
-python scripts/lora_extraction/merge_lora.py \
-  --base Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
-  --adapter adapter_r32.safetensors \
-  --ft path/to/your/finetuned_model \
-  --output merged_model
+bash scripts/finetune/finetune_hunyuan.sh
+bash scripts/finetune/finetune_mochi_lora_mix.sh
 ```

-| Argument | Description |
-|----------|-------------|
-| `--base` | Base model path |
-| `--adapter` | LoRA adapter file |
-| `--ft` | Finetuned model (for config reference) |
-| `--output` | Output directory for merged model |
-
-### Validate Merged Model
-
-Compare the merged model against the original finetuned model:
-
-```bash
-python scripts/lora_extraction/lora_inference_comparison.py \
-  --base merged_model \
-  --ft path/to/your/finetuned_model \
-  --adapter NONE \
-  --output-dir results \
-  --prompt "A cat sitting on a windowsill" \
-  --compute-ssim \
-  --compute-lpips
-```
-
-## Training Examples
-
-Ready-to-run training scripts are available for multiple models:
-
-**→ [Browse all training examples](examples/examples_training_index.md)**
-
-| Model | Type | Example |
-|-------|------|---------|
-| Wan2.1 T2V 1.3B | T2V | `examples/training/finetune/wan_t2v_1.3B/crush_smol/` |
-| Wan2.1 I2V 14B | I2V | `examples/training/finetune/wan_i2v_14B_480p/crush_smol/` |
-| Wan2.1-Fun 1.3B InP | I2V | `examples/training/finetune/Wan2.1-Fun-1.3B-InP/crush_smol/` |
-| Wan2.1 VSA | T2V/I2V | `examples/training/finetune/Wan2.1-VSA/Wan-Syn-Data/` |
-
-Each example includes:
-
- `download_dataset.sh` — download sample data
- `preprocess_*.sh` — run preprocessing
- `finetune_*.sh` — full finetune launcher
- `finetune_*_lora.sh` — LoRA finetune launcher
- `validation.json` — validation prompts
+For Image-Video Mixture Fine-tuning, make sure to enable the `--group_frame` option in your script.
@@ -1,67 +0,0 @@
-# Training Overview
-
-FastVideo supports finetuning video diffusion models on custom datasets. This page explains what data you need and how to get started.
-
-## Data Requirements
-
-To save GPU memory during training, FastVideo precomputes embeddings and latents ahead of time. This eliminates the need to load the text encoder and VAE during training, significantly reducing memory usage.
-
-### Text-to-Video (T2V) Finetuning
-
-For T2V models, you need:
-
-| Component | Description |
-|-----------|-------------|
-| **Text embeddings** | Precomputed embeddings from the model's text encoder (e.g., T5 or LLaMA). Stored as numpy arrays in Parquet files. |
-| **Video latents** | VAE-encoded representations of your training videos. Each video is encoded into a compressed latent tensor. |
-
-### Image-to-Video (I2V) Finetuning
-
-For I2V models, you need everything from T2V plus additional image conditioning. Note that not all I2V architectures require encoded images—this depends on how the model conditions on the input frame. Wan2.1 and Wan2.2 A14B I2V models do require these additional components:
-
-| Component | Description |
-|-----------|-------------|
-| **Text embeddings** | Same as T2V—precomputed from the text encoder. |
-| **Video latents** | Same as T2V—VAE-encoded video representations. |
-| **First frame latent** | VAE-encoded representation of the first frame, used as the conditioning image. |
-| **CLIP features** | Image embeddings from a CLIP vision encoder for the conditioning frame. |
-
-## Preprocessing
-
-Before training, you need to preprocess your raw videos and captions into Parquet files containing precomputed latents and embeddings.
-
-FastVideo supports two input formats:
-
- **HuggingFace datasets** — load directly from HF Hub or local HF datasets
- **Merged datasets** — local folder with videos and a `videos2caption.json` metadata file
-
-**→ See [Data Preprocessing](data_preprocess.md) for full details and examples.**
-
-## Training Examples
-
-Ready-to-run examples with preprocessing scripts, training launchers, and validation configs are available for multiple models and datasets:
-
-**→ [Browse all training examples](examples/examples_training_index.md)**
-
-Each example includes:
-
- `download_dataset.sh` — download sample data
- `preprocess_*.sh` — run preprocessing
- `finetune_*.sh` — launch training (full finetune or LoRA)
- `validation.json` — validation prompts for checkpoints
-
-## Training Methods
-
-FastVideo supports several training approaches:
-
-| Method | Use Case |
-|--------|----------|
-| **Full finetune** | Adapt entire model to a new domain or style |
-| **LoRA finetune** | Lightweight adaptation with frozen base weights |
-| **VSA finetune** | Finetune with Variable Sparse Attention for efficiency |
-
-## Next Steps
-
-1. **Get started**: Pick an example from the [training examples index](examples/examples_training_index.md)
-2. **Prepare data**: Follow [data preprocessing](data_preprocess.md) for your own dataset
-3. **Run inference**: After training, see [inference examples](../inference/examples/examples_inference_index.md)
@@ -1,71 +0,0 @@
-# LoRA Extraction and Merging
-
-Tools for extracting and merging LoRA adapters for FastVideo models.
-
-## Extract LoRA Adapter
-
-```bash
-python scripts/lora_extraction/extract_lora.py \
-  --base Wan-AI/Wan2.2-TI2V-5B-Diffusers \
-  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
-  --out adapter_r32.safetensors \
-  --rank 32
-```
-
-**Options:**
-
- `--base`: Base model (HuggingFace ID or local path)
- `--ft`: Fine-tuned model (HuggingFace ID or local path)
- `--out`: Output adapter file
- `--rank`: LoRA rank (16, 32, 64, 128)
- `--full-rank`: Extract full-rank adapter (optional)
-
-## Merge Adapter
-
-```bash
-python scripts/lora_extraction/merge_lora.py \
-  --base Wan-AI/Wan2.2-TI2V-5B-Diffusers \
-  --adapter adapter_r32.safetensors \
-  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
-  --output merged_model
-```
-
-**Options:**
-
- `--base`: Base model (HuggingFace ID or local path)
- `--adapter`: LoRA adapter file (.safetensors)
- `--ft`: Fine-tuned model (for configuration)
- `--output`: Output directory
-
-## Validate Quality (Optional)
-
-```bash
-python scripts/lora_extraction/lora_inference_comparison.py \
-  --base merged_model \
-  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
-  --adapter NONE \
-  --output-dir results \
-  --prompt "A cat sitting on a windowsill" \
-  --seed 42 \
-  --height 480 \
-  --width 480 \
-  --num-frames 49 \
-  --num-inference-steps 32 \
-  --compute-ssim \
-  --compute-lpips
-```
-
-**Options:**
-
- `--base`: Merged model or base model path
- `--ft`: Fine-tuned model (reference)
- `--adapter`: Path to adapter or NONE
- `--output-dir`: Output directory
- `--prompt`: Text prompt (default: "A cat sitting on a windowsill")
- `--seed`: Random seed (default: 42)
- `--height`: Video height (default: 480)
- `--width`: Video width (default: 832)
- `--num-frames`: Number of frames (default: 49)
- `--num-inference-steps`: Inference steps (default: 32)
- `--compute-ssim`: Compute SSIM metric
- `--compute-lpips`: Compute LPIPS metric
@@ -1,19 +0,0 @@
-# Self-Forcing Distillation for SFWan2.1 T2V 1.3B
-
-These scripts demonstrate self-forcing distillation (SFwan) for the causal Wan2.1 T2V 1.3B model. The workflow mirrors DMD2 while injecting self-forcing blocks so the student can autoregressively refine later frames.
-
-## Run the recipe
-1. Download the preprocessed text-video dataset:
-   ```bash
-   bash examples/distill/SFWan2.1-T2V/download_dataset.sh
-   ```
-2. (Optional) Regenerate parquet shards locally:
-   ```bash
-   bash examples/distill/SFWan2.1-T2V/preprocess_data.sh
-   ```
-3. Launch self-forcing distillation with your cluster settings:
-   ```bash
-   sbatch examples/distill/SFWan2.1-T2V/distill_dmd_t2v_1.3B.sh
-   ```
-
-Update the dataset paths and wandb credentials inside the script before running on your environment.
@@ -12,7 +12,7 @@ def main():
        "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=False,
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -1,51 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
-
-
-def main():
-    # Point this to your local diffusers model dir (or replace with a HF model ID).
-    model_path = "KyleShao/Cosmos-Predict2.5-2B-Diffusers"
-
-    generator = VideoGenerator.from_pretrained(
-        model_path,
-        num_gpus=1,
-        use_fsdp_inference=False,  # set True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True,
-    )
-
-    sampling_param = SamplingParam.from_pretrained(model_path)
-
-    # image2world example from official repo
-    image_path = "images/bus_terminal.jpg"
-
-    prompt = (
-        "A nighttime city bus terminal gradually shifts from stillness to subtle movement. "
-        "At first, multiple double-decker buses are parked under the glow of overhead lights, "
-        "with a central bus labeled '87D' facing forward and stationary. "
-        "As the video progresses, the bus in the middle moves ahead slowly, its headlights brightening the surrounding area "
-        "and casting reflections onto adjacent vehicles. "
-        "The motion creates space in the lineup, signaling activity within the otherwise quiet station. "
-        "It then comes to a smooth stop, resuming its position in line. "
-        "Overhead signage in Chinese characters remains illuminated, enhancing the vibrant, urban night scene."
-    )
-
-    generator.generate_video(
-        prompt,
-        sampling_param=sampling_param,
-        image_path=str(image_path),
-        num_cond_frames=1,
-        output_path="outputs_video/cosmos2_5_i2w.mp4",
-        save_video=True,
-    )
-
-    generator.shutdown()
-
-
-if __name__ == "__main__":
-    main()
-
-
@@ -1,51 +0,0 @@
-from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
-
-
-def main():
-    # Point this to your local diffusers model dir (or replace with a HF model ID).
-    model_path = "KyleShao/Cosmos-Predict2.5-2B-Diffusers"
-
-    generator = VideoGenerator.from_pretrained(
-        model_path,
-        num_gpus=1,
-        use_fsdp_inference=False,  # set True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True,
-    )
-
-    # Load default sampling parameters (negative_prompt, resolution, steps, etc.)
-    sampling_param = SamplingParam.from_pretrained(model_path)
-
-    prompt = (
-        "A high-definition video captures the precision of robotic welding in an industrial setting. "
-        "The first frame showcases a robotic arm, equipped with a welding torch, positioned over a large metal structure. "
-        "The welding process is in full swing, with bright sparks and intense light illuminating the scene, "
-        "creating a vivid display of blue and white hues. "
-        "A significant amount of smoke billows around the welding area, partially obscuring the view but emphasizing the heat and activity. "
-        "The background reveals parts of the workshop environment, including a ventilation system and various pieces of machinery, "
-        "indicating a busy and functional industrial workspace. "
-        "As the video progresses, the robotic arm maintains its steady position, continuing the welding process and moving to its left. "
-        "The welding torch consistently emits sparks and light, and the smoke continues to rise, diffusing slightly as it moves upward. "
-        "The metal surface beneath the torch shows ongoing signs of heating and melting. "
-        "The scene retains its industrial ambiance, with the welding sparks and smoke dominating the visual field, "
-        "underscoring the ongoing nature of the welding operation."
-    )
-
-    generator.generate_video(
-        prompt,
-        sampling_param=sampling_param,
-        output_path="outputs_video/cosmos2_5_t2w.mp4",
-        save_video=True,
-    )
-
-    generator.shutdown()
-
-
-if __name__ == "__main__":
-    main()
-
-
-
@@ -1,54 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-from fastvideo import VideoGenerator
-from fastvideo.configs.sample import SamplingParam
-
-
-def main():
-    # Point this to your local diffusers model dir (or replace with a HF model ID).
-    model_path = "KyleShao/Cosmos-Predict2.5-2B-Diffusers"
-
-    generator = VideoGenerator.from_pretrained(
-        model_path,
-        num_gpus=1,
-        use_fsdp_inference=False,  # set True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True,
-    )
-
-    sampling_param = SamplingParam.from_pretrained(model_path)
-
-    # video2world example from official repo
-    video_path = "videos/robot_pouring.mp4"
-
-    prompt = (
-        "A robotic arm, primarily white with black joints and cables, is shown in a clean, modern indoor setting with a white tabletop. "
-        "The arm, equipped with a gripper holding a small, light green pitcher, is positioned above a clear glass containing a reddish-brown liquid and a spoon. "
-        "The robotic arm is in the process of pouring a transparent liquid into the glass. "
-        "To the left of the pitcher, there is an opened jar with a similar reddish-brown substance visible through its transparent body. "
-        "In the background, a vase with white flowers and a brown couch are partially visible, adding to the contemporary ambiance. "
-        "The lighting is bright, casting soft shadows on the table. "
-        "The robotic arm's movements are smooth and controlled, demonstrating precision in its task. "
-        "As the video progresses, the robotic arm completes the pour, leaving the glass half-filled with the reddish-brown liquid. "
-        "The jar remains untouched throughout the sequence, and the spoon inside the glass remains stationary. "
-        "The other robotic arm on the right side also stays stationary throughout the video. "
-        "The final frame captures the robotic arm with the pitcher finishing the pour, with the glass now filled to a higher level, while the pitcher is slightly tilted but still held securely by the gripper."
-    )
-
-    generator.generate_video(
-        prompt,
-        sampling_param=sampling_param,
-        video_path=str(video_path),
-        num_cond_frames=1,
-        output_path="outputs_video/cosmos2_5_v2w.mp4",
-        save_video=True,
-    )
-
-    generator.shutdown()
-
-
-if __name__ == "__main__":
-    main()
-
-
@@ -14,7 +14,7 @@ def main():
        model_name,
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        # Adjust these offload parameters if you have < 32GB of VRAM
        text_encoder_cpu_offload=True,
        pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
@@ -12,7 +12,7 @@ def main():
        "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True,
        vae_cpu_offload=True,
        text_encoder_cpu_offload=True,
@@ -39,4 +39,4 @@ def main():


 if __name__ == "__main__":
-    main()
+    main()
@@ -1,43 +0,0 @@
-from fastvideo import VideoGenerator
-import json
-# from fastvideo.configs.sample import SamplingParam
-
-OUTPUT_PATH = "video_samples_hy15_1080p"
-def main():
-    # FastVideo will automatically use the optimal default arguments for the
-    # model.
-    # If a local path is provided, FastVideo will make a best effort
-    # attempt to identify the optimal arguments.
-    generator = VideoGenerator.from_pretrained(
-        "weizhou03/HunyuanVideo-1.5-Diffusers-1080p-2SR", # 480p -> 720p -> 1080p
-        # or "weizhou03/HunyuanVideo-1.5-Diffusers-1080p" # 720p -> 1080p
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=True,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-        # image_encoder_cpu_offload=False,
-    )
-
-    prompt = (
-        "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
-        "wide with interest. The playful yet serene atmosphere is complemented by soft "
-        "natural light filtering through the petals. Mid-shot, warm and cheerful tones."
-    )
-
-    video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, negative_prompt="")
-
-    prompt2 = (
-        "A majestic lion strides across the golden savanna, its powerful frame "
-        "glistening under the warm afternoon sun. The tall grass ripples gently in "
-        "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "
-        "embodying the raw energy of the wild. Low angle, steady tracking shot, "
-        "cinematic.")
-
-    video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, negative_prompt="")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,66 +0,0 @@
-from fastvideo import VideoGenerator
-from fastvideo.models.dits.hyworld.resolution_utils import get_resolution_from_image
-
-# Default prompt from HY-WorldPlay run.sh
-DEFAULT_PROMPT = 'A paved pathway leads towards a stone arch bridge spanning a calm body of water.  Lush green trees and foliage line the path and the far bank of the water. A traditional-style pavilion with a tiered, reddish-brown roof sits on the far shore. The water reflects the surrounding greenery and the sky.  The scene is bathed in soft, natural light, creating a tranquil and serene atmosphere. The pathway is composed of large, rectangular stones, and the bridge is constructed of light gray stone.  The overall composition emphasizes the peaceful and harmonious nature of the landscape.'
-DEFAULT_IMAGE = 'https://raw.githubusercontent.com/Tencent-Hunyuan/HY-WorldPlay/main/assets/img/test.png'
-
-OUTPUT_PATH = "video_samples_hyworld"
-def main():
-    import argparse
-
-    # pose: (a, w, s, d) - (15, 31)
-    # num_frames: (61, 125)
-    parser = argparse.ArgumentParser(description="HYWorld video generation with FastVideo")
-    parser.add_argument("--prompt", type=str, default=DEFAULT_PROMPT, help="Text prompt for video generation")
-    parser.add_argument("--image", type=str, default=DEFAULT_IMAGE, help="Path or URL to input image")
-    parser.add_argument("--pose", type=str, default='w-31', help="Pose string (e.g., 'a-31', 'w-31', 's-31', 'd-31')")
-    parser.add_argument("--output_path", type=str, default=OUTPUT_PATH, help="Output video path")
-    parser.add_argument("--num-frames", type=int, default=125, help="Number of frames")
-    parser.add_argument("--seed", type=int, default=1, help="Random seed")
-    parser.add_argument("--resolution", type=str, default="480p", help="Only support 480p for now")
-    args = parser.parse_args()
-
-    # Automatically determine resolution from input image
-    HEIGHT, WIDTH = get_resolution_from_image(args.image, args.resolution)
-    print(f"Image: {args.image}")
-    print(f"Pose: {args.pose}")
-    print(f"Resolution: {HEIGHT}x{WIDTH} (from {args.resolution} buckets)")
-    print(f"Num frames: {args.num_frames}")
-    print(f"Output path: {args.output_path}")
-
-    # Initialize generator
-    print("\nInitializing VideoGenerator for HYWorld...")
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/HY-WorldPlay-Bidirectional-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True,
-        image_encoder_cpu_offload=True,
-    )
-
-    # Generate video
-    # The pose string is automatically converted to camera matrices by the pipeline
-    print("\nGenerating video...")
-    generator.generate_video(
-        prompt=args.prompt,
-        image_path=args.image,
-        pose=args.pose,  # Camera trajectory control
-        output_path=args.output_path,
-        save_video=True,
-        negative_prompt="",
-        num_frames=args.num_frames,
-        fps=24,
-        height=HEIGHT,
-        width=WIDTH,
-        seed=args.seed,
-    )
-
-    print(f"\nVideo saved to: {args.output_path}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,210 +0,0 @@
-"""
-LongCat Image-to-Video (I2V) Example Script
-
-This script demonstrates LongCat I2V inference using the FastVideo Python API.
-LongCat I2V takes an input image and generates a video from it.
-
-It runs both basic generation (50 steps) and distill+refine generation
-(16 steps distill + 50 steps refinement to 720p with BSA).
-
-Usage:
-    python examples/inference/basic/basic_longcat_i2v.py
-
-Note:
-    Refinement uses 768x768 dimensions where latent (48x48) is divisible by 8,
-    compatible with BSA chunks [4, 4, 8].
-"""
-
-import glob
-import os
-
-from fastvideo import VideoGenerator
-
-# Common prompts and settings matching the shell script examples
-PROMPT = (
-    "A woman sits at a wooden table by the window in a cozy café. She reaches out "
-    "with her right hand, picks up the white coffee cup from the saucer, and gently "
-    "brings it to her lips to take a sip. After drinking, she places the cup back on "
-    "the table and looks out the window, enjoying the peaceful atmosphere."
-)
-
-NEGATIVE_PROMPT = (
-    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
-    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
-    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
-    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
-    "three legs, many people in the background, walking backwards"
-)
-
-# Input image path
-IMAGE_PATH = "assets/girl.png"
-
-SEED = 42
-
-
-def basic_generation():
-    """
-    Run basic LongCat I2V generation (50 steps at 480p).
-    
-    This uses the full 50-step denoising process for highest quality.
-    """
-    print("=" * 60)
-    print("LongCat I2V: Basic Generation (50 steps, 480p)")
-    print("=" * 60)
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-I2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-    )
-    
-    output_path = "outputs_video/longcat_i2v_basic"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        image_path=IMAGE_PATH,
-        output_path=output_path,
-        save_video=True,
-        height=480,
-        width=480,  # Square
-        num_frames=93,
-        num_inference_steps=50,
-        fps=15,
-        guidance_scale=4.0,
-        seed=SEED,
-    )
-    
-    print(f"\nBasic generation complete! Video saved to: {output_path}")
-    generator.shutdown()
-
-
-def distill_refine_generation():
-    """
-    Run LongCat I2V with distill+refine pipeline (16 steps + refinement to 768p).
-    
-    This uses the distilled LoRA for fast 480p generation (16 steps),
-    then refines to 768p using the refinement LoRA with BSA enabled.
-    """
-    print("\n" + "=" * 60)
-    print("LongCat I2V: Distill + Refine Pipeline")
-    print("=" * 60)
-    
-    # Stage 1: Distilled generation (16 steps at 480p)
-    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
-    print("-" * 40)
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-I2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
-        lora_nickname="distilled",
-    )
-    
-    distill_output_path = "outputs_video/longcat_i2v_distill"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        image_path=IMAGE_PATH,
-        output_path=distill_output_path,
-        save_video=True,
-        height=480,
-        width=480,  # Square
-        num_frames=93,
-        num_inference_steps=16,
-        fps=15,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
-    generator.shutdown()
-    
-    # Stage 2: Refinement (480p -> 768p)
-    print("\n[Stage 2] Refinement (480p -> 768p with BSA)")
-    print("-" * 40)
-    
-    # Find the actual saved video file from stage 1
-    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
-    if not video_files:
-        raise FileNotFoundError(f"No video file found in {distill_output_path}")
-    # Use the most recently created video file
-    distill_video_path = max(video_files, key=os.path.getmtime)
-    print(f"Using stage 1 video: {distill_video_path}")
-    
-    # Create a new generator with refinement LoRA and BSA enabled
-    # Note: Refinement uses the T2V model (not I2V) since it's upscaling the generated video
-    # For BSA [4, 4, 8]: latent must be divisible by 8
-    # 768x768: latent 48x48, 48%8=0 ✓
-    refine_generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-T2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=True,
-        bsa_sparsity=0.875,
-        bsa_chunk_q=[4, 4, 4],
-        bsa_chunk_k=[4, 4, 4],
-        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
-        lora_nickname="refinement",
-    )
-    
-    refine_output_path = "outputs_video/longcat_i2v_refine_720p"
-    
-    refine_generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        output_path=refine_output_path,
-        save_video=True,
-        refine_from=distill_video_path,
-        t_thresh=0.5,
-        spatial_refine_only=False,
-        num_cond_frames=0,
-        height=720,
-        width=720,
-        num_inference_steps=50,
-        fps=30,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Refinement complete! Video saved to: {refine_output_path}")
-    refine_generator.shutdown()
-
-
-def main():
-    """Run both basic and distill+refine generation pipelines."""
-    print("\n" + "=" * 60)
-    print("LongCat Image-to-Video Example")
-    print("=" * 60 + "\n")
-    
-    # Run basic generation
-    basic_generation()
-    
-    # Run distill+refine pipeline
-    distill_refine_generation()
-    
-    print("\n" + "=" * 60)
-    print("All generations complete!")
-    print("=" * 60)
-
-
-if __name__ == "__main__":
-    main()
-
-
@@ -1,198 +0,0 @@
-"""
-LongCat Text-to-Video (T2V) Example Script
-
-This script demonstrates LongCat T2V inference using the FastVideo Python API.
-It runs both basic generation (50 steps) and distill+refine generation
-(16 steps distill + 50 steps refinement to 720p).
-
-Usage:
-    python examples/inference/basic/basic_longcat_t2v.py
-"""
-
-import glob
-import os
-
-from fastvideo import VideoGenerator
-
-# Common prompts and settings matching the shell script examples
-PROMPT = (
-    "In a realistic photography style, a white boy around seven or eight years old "
-    "sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. "
-    "He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a "
-    "medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, "
-    "who eagerly licks it with its tongue. The sun is shining brightly, and the background "
-    "features a green lawn and several tall trees, creating a warm and loving scene."
-)
-
-NEGATIVE_PROMPT = (
-    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
-    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
-    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
-    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
-    "three legs, many people in the background, walking backwards"
-)
-
-SEED = 42
-
-
-def basic_generation():
-    """
-    Run basic LongCat T2V generation (50 steps at 480p).
-    
-    This uses the full 50-step denoising process for highest quality.
-    """
-    print("=" * 60)
-    print("LongCat T2V: Basic Generation (50 steps, 480p)")
-    print("=" * 60)
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-T2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-    )
-    
-    output_path = "outputs_video/longcat_t2v_basic"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        output_path=output_path,
-        save_video=True,
-        height=480,
-        width=832,
-        num_frames=93,
-        num_inference_steps=50,
-        fps=15,
-        guidance_scale=4.0,
-        seed=SEED,
-    )
-    
-    print(f"\nBasic generation complete! Video saved to: {output_path}")
-    generator.shutdown()
-
-
-def distill_refine_generation():
-    """
-    Run LongCat T2V with distill+refine pipeline (16 steps + refinement to 720p).
-    
-    This uses the distilled LoRA for fast 480p generation (16 steps),
-    then refines to 720p using the refinement LoRA with BSA enabled.
-    """
-    print("\n" + "=" * 60)
-    print("LongCat T2V: Distill + Refine Pipeline")
-    print("=" * 60)
-    
-    # Stage 1: Distilled generation (16 steps at 480p)
-    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
-    print("-" * 40)
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-T2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
-        lora_nickname="distilled",
-    )
-    
-    distill_output_path = "outputs_video/longcat_t2v_distill"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        output_path=distill_output_path,
-        save_video=True,
-        height=480,
-        width=832,
-        num_frames=93,
-        num_inference_steps=16,
-        fps=15,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
-    generator.shutdown()
-    
-    # Stage 2: Refinement (480p -> 720p)
-    print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
-    print("-" * 40)
-    
-    # Find the actual saved video file from stage 1
-    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
-    if not video_files:
-        raise FileNotFoundError(f"No video file found in {distill_output_path}")
-    # Use the most recently created video file
-    distill_video_path = max(video_files, key=os.path.getmtime)
-    print(f"Using stage 1 video: {distill_video_path}")
-    
-    # Create a new generator with refinement LoRA and BSA enabled
-    refine_generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-T2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=True,
-        bsa_sparsity=0.875,
-        bsa_chunk_q=[4, 4, 8],
-        bsa_chunk_k=[4, 4, 8],
-        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
-        lora_nickname="refinement",
-    )
-    
-    refine_output_path = "outputs_video/longcat_t2v_refine_720p"
-    
-    refine_generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        output_path=refine_output_path,
-        save_video=True,
-        refine_from=distill_video_path,
-        t_thresh=0.5,
-        spatial_refine_only=False,
-        num_cond_frames=0,
-        height=720,
-        width=1280,
-        num_inference_steps=50,
-        fps=30,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Refinement complete! Video saved to: {refine_output_path}")
-    refine_generator.shutdown()
-
-
-def main():
-    """Run both basic and distill+refine generation pipelines."""
-    print("\n" + "=" * 60)
-    print("LongCat Text-to-Video Example")
-    print("=" * 60 + "\n")
-    
-    # Run basic generation
-    basic_generation()
-    
-    # Run distill+refine pipeline
-    distill_refine_generation()
-    
-    print("\n" + "=" * 60)
-    print("All generations complete!")
-    print("=" * 60)
-
-
-if __name__ == "__main__":
-    main()
-
-
@@ -1,228 +0,0 @@
-"""
-LongCat Video Continuation (VC) Example Script
-
-This script demonstrates LongCat VC inference using the FastVideo Python API.
-LongCat VC takes an input video and generates a continuation of it.
-
-It runs both basic generation (50 steps) and distill+refine generation
-(16 steps distill + 50 steps refinement to 720p).
-
-Usage:
-    python examples/inference/basic/basic_longcat_vc.py
-
-Prerequisites:
-    - Ensure the input video exists at assets/motorcycle.mp4
-      (or provide your own video)
-"""
-
-import glob
-import os
-
-from fastvideo import VideoGenerator
-
-# Common prompts and settings matching the shell script examples
-PROMPT = (
-    "A person rides a motorcycle along a long, straight road that stretches between "
-    "a body of water and a forested hillside. The rider steadily accelerates, keeping "
-    "the motorcycle centered between the guardrails, while the scenery passes by on "
-    "both sides. The video captures the journey from the rider's perspective, emphasizing "
-    "the sense of motion and adventure."
-)
-
-NEGATIVE_PROMPT = (
-    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
-    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
-    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
-    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
-    "three legs, many people in the background, walking backwards"
-)
-
-# Input video path
-VIDEO_PATH = "assets/motorcycle.mp4"
-
-# Number of conditioning frames from the input video
-NUM_COND_FRAMES = 13
-
-SEED = 42
-
-
-def basic_generation():
-    """
-    Run basic LongCat VC generation (50 steps at 480p).
-    
-    This uses the full 50-step denoising process for highest quality.
-    """
-    print("=" * 60)
-    print("LongCat VC: Basic Generation (50 steps, 480p)")
-    print("=" * 60)
-    
-    # Check if video exists
-    if not os.path.exists(VIDEO_PATH):
-        raise FileNotFoundError(
-            f"Video not found at {VIDEO_PATH}. "
-            "Please provide a valid video path."
-        )
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-VC-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-    )
-    
-    output_path = "outputs_video/longcat_vc_basic"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        video_path=VIDEO_PATH,
-        num_cond_frames=NUM_COND_FRAMES,
-        output_path=output_path,
-        save_video=True,
-        height=480,
-        width=832,
-        num_frames=93,
-        num_inference_steps=50,
-        fps=15,
-        guidance_scale=4.0,
-        seed=SEED,
-    )
-    
-    print(f"\nBasic generation complete! Video saved to: {output_path}")
-    generator.shutdown()
-
-
-def distill_refine_generation():
-    """
-    Run LongCat VC with distill+refine pipeline (16 steps + refinement to 720p).
-    
-    This uses the distilled LoRA for fast 480p generation (16 steps),
-    then refines to 720p using the refinement LoRA with BSA enabled.
-    """
-    print("\n" + "=" * 60)
-    print("LongCat VC: Distill + Refine Pipeline")
-    print("=" * 60)
-    
-    # Check if video exists
-    if not os.path.exists(VIDEO_PATH):
-        raise FileNotFoundError(
-            f"Video not found at {VIDEO_PATH}. "
-            "Please provide a valid video path."
-        )
-    
-    # Stage 1: Distilled generation (16 steps at 480p)
-    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
-    print("-" * 40)
-    
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-VC-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=False,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=False,
-        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
-        lora_nickname="distilled",
-    )
-    
-    distill_output_path = "outputs_video/longcat_vc_distill"
-    
-    generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        video_path=VIDEO_PATH,
-        num_cond_frames=NUM_COND_FRAMES,
-        output_path=distill_output_path,
-        save_video=True,
-        height=480,
-        width=832,
-        num_frames=93,
-        num_inference_steps=16,
-        fps=15,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
-    generator.shutdown()
-    
-    # Stage 2: Refinement (480p -> 720p)
-    print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
-    print("-" * 40)
-    
-    # Find the actual saved video file from stage 1
-    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
-    if not video_files:
-        raise FileNotFoundError(f"No video file found in {distill_output_path}")
-    # Use the most recently created video file
-    distill_video_path = max(video_files, key=os.path.getmtime)
-    print(f"Using stage 1 video: {distill_video_path}")
-    
-    # Create a new generator with refinement LoRA and BSA enabled
-    # Note: Refinement uses the T2V model (not VC) since it's upscaling the generated video
-    refine_generator = VideoGenerator.from_pretrained(
-        "FastVideo/LongCat-Video-T2V-Diffusers",
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=True,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=False,
-        enable_bsa=True,
-        bsa_sparsity=0.875,
-        bsa_chunk_q=[4, 4, 8],
-        bsa_chunk_k=[4, 4, 8],
-        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
-        lora_nickname="refinement",
-    )
-    
-    refine_output_path = "outputs_video/longcat_vc_refine_720p"
-    
-    refine_generator.generate_video(
-        prompt=PROMPT,
-        negative_prompt=NEGATIVE_PROMPT,
-        output_path=refine_output_path,
-        save_video=True,
-        refine_from=distill_video_path,
-        t_thresh=0.5,
-        spatial_refine_only=False,
-        num_cond_frames=0,  # For refinement, no conditioning frames
-        height=720,
-        width=1280,
-        num_inference_steps=50,
-        fps=30,
-        guidance_scale=1.0,
-        seed=SEED,
-    )
-    
-    print(f"Refinement complete! Video saved to: {refine_output_path}")
-    refine_generator.shutdown()
-
-
-def main():
-    """Run both basic and distill+refine generation pipelines."""
-    print("\n" + "=" * 60)
-    print("LongCat Video Continuation Example")
-    print("=" * 60 + "\n")
-    
-    # Run basic generation
-    basic_generation()
-    
-    # Run distill+refine pipeline
-    distill_refine_generation()
-    
-    print("\n" + "=" * 60)
-    print("All generations complete!")
-    print("=" * 60)
-
-
-if __name__ == "__main__":
-    main()
-
-
@@ -1,34 +0,0 @@
-from fastvideo import VideoGenerator
-
-PROMPT = (
-    "A warm sunny backyard. The camera starts in a tight cinematic close-up "
-    "of a woman and a man in their 30s, facing each other with serious "
-    "expressions. The woman, emotional and dramatic, says softly, \"That's "
-    "it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
-    "annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
-    "then mutters defensively, \"He's just having fun.\" The camera slowly "
-    "pans right, revealing the grandfather in the garden wearing enormous "
-    "butterfly wings, waving his arms in the air like he's trying to take "
-    "off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
-    "The woman covers her face, on the verge of tears. The tone is deadpan, "
-    "absurd, and quietly tragic."
-)
-
-
-def main() -> None:
-    generator = VideoGenerator.from_pretrained(
-        "FastVideo/LTX2-Distilled-Diffusers",
-        num_gpus=1,
-    )
-
-    output_path = "outputs_video/ltx2_basic/output_ltx2_distilled_t2v.mp4"
-    generator.generate_video(
-        prompt=PROMPT,
-        output_path=output_path,
-        save_video=True,
-    )
-    generator.shutdown()
-
-
-if __name__ == "__main__":
-    main()
@@ -1,5 +1,6 @@
 from fastvideo import VideoGenerator
-from fastvideo.models.dits.matrixgame.utils import create_action_presets
+from fastvideo.configs.pipelines.wan import MatrixGameI2V480PConfig
+from fastvideo.models.dits.matrix_game.utils import create_action_presets

 import torch

@@ -42,7 +43,7 @@ def main():
        config["model_path"],
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -1,98 +0,0 @@
-from fastvideo.entrypoints.streaming_generator import StreamingVideoGenerator
-from fastvideo.models.dits.matrixgame.utils import get_current_action_async, expand_action_to_frames
-
-import torch
-import asyncio
-
-# Available variants: "base_distilled_model", "gta_distilled_model", "templerun_distilled_model"
-# Each variant has different keyboard_dim:
-#   - base_distilled_model: keyboard_dim=4
-#   - gta_distilled_model: keyboard_dim=2
-#   - templerun_distilled_model: keyboard_dim=7 (keyboard only, no mouse)
-MODEL_VARIANT = "base_distilled_model"
-
-# Variant-specific settings
-VARIANT_CONFIG = {
-    "base_distilled_model": {
-        "model_path": "FastVideo/Matrix-Game-2.0-Base-Diffusers",
-        "keyboard_dim": 4,
-        "mode": "universal",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
-    },
-    "gta_distilled_model": {
-        "model_path": "FastVideo/Matrix-Game-2.0-GTA-Diffusers",
-        "keyboard_dim": 2,
-        "mode": "gta_drive",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
-    },
-    "templerun_distilled_model": {
-        "model_path": "FastVideo/Matrix-Game-2.0-TempleRun-Diffusers",
-        "keyboard_dim": 7,
-        "mode": "templerun",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
-    },
-}
-
-
-OUTPUT_PATH = "video_samples_matrixgame2"
-async def main():
-    # FastVideo will automatically use the optimal default arguments for the
-    # model.
-    # If a local path is provided, FastVideo will make a best effort
-    # attempt to identify the optimal arguments.
-    config = VARIANT_CONFIG[MODEL_VARIANT]
-
-    generator = StreamingVideoGenerator.from_pretrained(
-        config["model_path"],
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=True, # DiT need to be offloaded for MoE
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
-        pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
-    )
-
-    max_blocks = 50
-    num_frames = 597    
-    actions = {
-        "keyboard": torch.zeros((num_frames, config["keyboard_dim"])),
-        "mouse": torch.zeros((num_frames, 2))
-    }
-    grid_sizes = torch.tensor([150, 44, 80])
-    mode = config["mode"]
-
-    generator.reset(
-        prompt="",
-        image_path=config["image_url"],
-        mouse_cond=actions["mouse"].unsqueeze(0),
-        keyboard_cond=actions["keyboard"].unsqueeze(0),
-        grid_sizes=grid_sizes,
-        num_frames=num_frames,
-        height=352,
-        width=640,
-        num_inference_steps=50,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-    )
-    print("Initialization complete.")
-
-    for block_id in range(max_blocks):
-        print(f"\n=== Block {block_id + 1}/{max_blocks} ===")
-        
-        action = await get_current_action_async(mode)
-        keyboard_cond, mouse_cond = expand_action_to_frames(action, 12)
-        await generator.step_async(keyboard_cond, mouse_cond)
-        
-        if (await asyncio.to_thread(input, "\nContinue? (y/n): ")).lower() == 'n':
-            break
-
-    # Save final video
-    generator.finalize()
-    generator.shutdown()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
@@ -13,7 +13,7 @@ def main():
        model_name,
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        text_encoder_cpu_offload=False,
        dit_cpu_offload=False,
    )
@@ -14,7 +14,7 @@ def main():
        "FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        dit_precision="fp32",
        vae_cpu_offload=False,
@@ -14,7 +14,7 @@ def main():
        "rand0nmr/SFWan2.2-T2V-A14B-Diffusers",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -1,55 +0,0 @@
-import os
-
-# Set SLA attention backend BEFORE fastvideo imports
-os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "SLA_ATTN"
-
-from fastvideo import VideoGenerator
-
-OUTPUT_PATH = "video_samples_turbodiffusion"
-
-
-def main() -> None:
-    # TurboDiffusion: 1-4 step video generation using RCM scheduler + SLA attention
-    # FastVideo will automatically use TurboDiffusionPipeline when specified
-    generator = VideoGenerator.from_pretrained(
-        "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers",
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-
-        # set to false if using RTX 4090 
-        # pin_cpu_memory=False,
-    )
-
-    # Generate videos with the same simple API, regardless of GPU count
-    # TurboDiffusion defaults: guidance_scale=1.0 and num_inference_steps=4 (from config)
-    prompt = (
-        "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
-        "wide with interest. The playful yet serene atmosphere is complemented by soft "
-        "natural light filtering through the petals. Mid-shot, warm and cheerful tones."
-    )
-    video = generator.generate_video(
-        prompt,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-        seed=42,
-    )
-
-    # Generate another video with a different prompt, without reloading the model!
-    prompt2 = (
-        "A majestic lion strides across the golden savanna, its powerful frame "
-        "glistening under the warm afternoon sun. The tall grass ripples gently in "
-        "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "
-        "embodying the raw energy of the wild. Low angle, steady tracking shot, "
-        "cinematic."
-    )
-    video2 = generator.generate_video(
-        prompt2,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-        seed=42,
-    )
-
-
-if __name__ == "__main__":
-    main()
@@ -1,49 +0,0 @@
-import os
-
-# Set SLA attention backend BEFORE fastvideo imports
-os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "SLA_ATTN"
-
-from fastvideo import VideoGenerator
-
-OUTPUT_PATH = "video_samples_turbodiffusion_14B"
-
-
-def main() -> None:
-    # TurboDiffusion 14B: 1-4 step video generation using RCM scheduler + SLA attention
-    # FastVideo will automatically use TurboDiffusionPipeline when specified
-    generator = VideoGenerator.from_pretrained(
-        "loayrashid/TurboWan2.1-T2V-14B-Diffusers",
-        # 14B model needs more GPUs
-        num_gpus=2,
-    )
-
-    prompt = (
-        "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
-        "wide with interest. The playful yet serene atmosphere is complemented by soft "
-        "natural light filtering through the petals. Mid-shot, warm and cheerful tones."
-    )
-    video = generator.generate_video(
-        prompt,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-        seed=42,
-    )
-
-    # Generate another video with a different prompt, without reloading the model!
-    prompt2 = (
-        "A majestic lion strides across the golden savanna, its powerful frame "
-        "glistening under the warm afternoon sun. The tall grass ripples gently in "
-        "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "
-        "embodying the raw energy of the wild. Low angle, steady tracking shot, "
-        "cinematic."
-    )
-    video2 = generator.generate_video(
-        prompt2,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-        seed=42,
-    )
-
-
-if __name__ == "__main__":
-    main()
@@ -1,37 +0,0 @@
-import os
-
-# Set SLA attention backend BEFORE fastvideo imports
-os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "SLA_ATTN"
-
-from fastvideo import VideoGenerator
-
-# Use local model path
-MODEL_PATH = "loayrashid/TurboWan2.2-I2V-A14B-Diffusers"
-OUTPUT_PATH = "video_samples_turbodiffusion_i2v"
-
-
-def main() -> None:
-    # TurboDiffusion I2V: 1-4 step image-to-video generation
-    generator = VideoGenerator.from_pretrained(
-        MODEL_PATH,
-        num_gpus=2,
-    )
-
-    # Example prompt and image for I2V
-    prompt = ("Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside.")
-
-    # Use an example image path
-    image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
-
-
-    video = generator.generate_video(
-        prompt,
-        image_path=image_path,
-        output_path=OUTPUT_PATH,
-        save_video=True,
-        seed=42,
-    )
-
-
-if __name__ == "__main__":
-    main()
@@ -12,7 +12,7 @@ def main():
        "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory 
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -14,7 +14,7 @@ def main():
        # "alibaba-pai/Wan2.2-Fun-A14B-Control",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -12,7 +12,7 @@ def main():
        "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True, # DiT need to be offloaded for MoE
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -11,7 +11,7 @@ def main():
        model_name,
        # FastVideo will automatically handle distributed setup
        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
+        use_fsdp_inference=True,
        dit_cpu_offload=True,
        vae_cpu_offload=False,
        text_encoder_cpu_offload=True,
@@ -1,684 +0,0 @@
-import argparse
-import asyncio
-import os
-import time
-
-import gradio as gr
-import torch
-import uvicorn
-from fastapi import FastAPI, Request, HTTPException
-from fastapi.responses import HTMLResponse, FileResponse
-
-from fastvideo.entrypoints.streaming_generator import StreamingVideoGenerator
-from fastvideo.models.dits.matrixgame.utils import expand_action_to_frames
-
-
-VARIANT_CONFIG = {
-    "Matrix-Game-2.0-Base": {
-        "model_path": "FastVideo/Matrix-Game-2.0-Base-Diffusers",
-        "keyboard_dim": 4,
-        "mode": "universal",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
-    },
-    "Matrix-Game-2.0-GTA": {
-        "model_path": "FastVideo/Matrix-Game-2.0-GTA-Diffusers",
-        "keyboard_dim": 2,
-        "mode": "gta_drive",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
-    },
-    "Matrix-Game-2.0-TempleRun": {
-        "model_path": "FastVideo/Matrix-Game-2.0-TempleRun-Diffusers",
-        "keyboard_dim": 7,
-        "mode": "templerun",
-        "image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
-    },
-}
-
-MODEL_PATH_MAPPING = {
-    name: config["model_path"] for name, config in VARIANT_CONFIG.items()
-}
-
-
-CAM_VALUE = 0.1
-KEYBOARD_MAP_UNIVERSAL = {
-    "W (Forward)": [1, 0, 0, 0],
-    "S (Back)": [0, 1, 0, 0],
-    "A (Left)": [0, 0, 1, 0],
-    "D (Right)": [0, 0, 0, 1],
-    "Q (Stop)": [0, 0, 0, 0],
-}
-KEYBOARD_MAP_GTA = {
-    "W (Forward)": [1, 0],
-    "S (Back)": [0, 1],
-    "Q (Stop)": [0, 0],
-}
-KEYBOARD_MAP_TEMPLERUN = {
-    "Q (Run)": [1, 0, 0, 0, 0, 0, 0],
-    "W (Jump)": [0, 1, 0, 0, 0, 0, 0],
-    "S (Slide)": [0, 0, 1, 0, 0, 0, 0],
-    "Z (Turn Left)": [0, 0, 0, 1, 0, 0, 0],
-    "C (Turn Right)": [0, 0, 0, 0, 1, 0, 0],
-    "A (Left)": [0, 0, 0, 0, 0, 1, 0],
-    "D (Right)": [0, 0, 0, 0, 0, 0, 1],
-}
-
-
-CAMERA_MAP_UNIVERSAL = {
-    "U (Center)": [0, 0],
-    "I (Up)": [CAM_VALUE, 0],
-    "K (Down)": [-CAM_VALUE, 0],
-    "J (Left)": [0, -CAM_VALUE],
-    "L (Right)": [0, CAM_VALUE],
-}
-CAMERA_MAP_GTA = {
-    "Q (Straight)": [0, 0],
-    "A (Steer Left)": [0, -CAM_VALUE],
-    "D (Steer Right)": [0, CAM_VALUE],
-}
-
-def setup_model_environment(model_path: str) -> None:
-    # if "fullattn" in model_path.lower():
-    #     os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "FLASH_ATTN"
-    # else:
-    #     os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "VIDEO_SPARSE_ATTN"
-    os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "FLASH_ATTN"
-    os.environ["FASTVIDEO_STAGE_LOGGING"] = "1"
-
-def create_timing_display(inference_time, total_time, stage_execution_times, num_frames):
-    dit_denoising_time = f"{stage_execution_times[5]:.2f}s" if len(stage_execution_times) > 5 else "N/A"
-    
-    timing_html = f"""
-    <div style="margin: 10px 0;">
-        <h3 style="text-align: center; margin-bottom: 10px;">⏱️ Timing Breakdown</h3>
-        <div style="display: grid; grid-template-columns: repeat(5, 1fr); gap: 10px; margin-bottom: 10px;">
-            <div class="timing-card timing-card-highlight">
-                <div style="font-size: 20px;">🚀</div>
-                <div style="font-weight: bold; margin: 3px 0; font-size: 14px;">DiT Denoising</div>
-                <div style="font-size: 16px; color: #ffa200; font-weight: bold;">{dit_denoising_time}</div>
-            </div>
-            <div class="timing-card">
-                <div style="font-size: 20px;">🧠</div>
-                <div style="font-weight: bold; margin: 3px 0; font-size: 14px;">E2E (w. vae/text encoder)</div>
-                <div style="font-size: 16px; color: #2563eb;">{inference_time:.2f}s</div>
-            </div>
-            <div class="timing-card">
-                <div style="font-size: 20px;">🎬</div>
-                <div style="font-weight: bold; margin: 3px 0; font-size: 14px;">Video Encoding</div>
-                <div style="font-size: 16px; color: #dc2626;">N/A</div>
-            </div>
-            <div class="timing-card">
-                <div style="font-size: 20px;">🌐</div>
-                <div style="font-weight: bold; margin: 3px 0; font-size: 14px;">Network Transfer</div>
-                <div style="font-size: 16px; color: #059669;">N/A</div>
-            </div>
-            <div class="timing-card">
-                <div style="font-size: 20px;">📊</div>
-                <div style="font-weight: bold; margin: 3px 0; font-size: 14px;">Total Processing</div>
-                <div style="font-size: 18px; color: #0277bd;">{total_time:.2f}s</div>
-            </div>
-        </div>"""
-    
-    if inference_time > 0:
-        fps = num_frames / inference_time
-        timing_html += f"""
-        <div class="performance-card" style="margin-top: 15px;">
-            <span style="font-weight: bold;">Generation Speed: </span>
-            <span style="font-size: 18px; color: #6366f1; font-weight: bold;">{fps:.1f} frames/second</span>
-        </div>"""
-    
-    return timing_html + "</div>"
-
-def get_action_tensors(mode: str, keyboard_key: str, mouse_key: str | None):
-    if mode == "universal":
-        keyboard = torch.tensor(KEYBOARD_MAP_UNIVERSAL.get(keyboard_key, [0, 0, 0, 0])).cuda()
-        mouse = torch.tensor(CAMERA_MAP_UNIVERSAL.get(mouse_key, [0, 0])).cuda()
-    elif mode == "gta_drive":
-        keyboard = torch.tensor(KEYBOARD_MAP_GTA.get(keyboard_key, [0, 0])).cuda()
-        mouse = torch.tensor(CAMERA_MAP_GTA.get(mouse_key, [0, 0])).cuda()
-    elif mode == "templerun":
-        keyboard = torch.tensor(KEYBOARD_MAP_TEMPLERUN.get(keyboard_key, [1, 0, 0, 0, 0, 0, 0])).cuda()
-        mouse = None
-    else:
-        raise ValueError(f"Unknown mode: {mode}")
-    
-    return {"keyboard": keyboard, "mouse": mouse}
-
-def create_gradio_interface(generators: dict[str, StreamingVideoGenerator], loaded_model_name: str):
-    initial_config = VARIANT_CONFIG.get(loaded_model_name, VARIANT_CONFIG["Matrix-Game-2.0-Base"])
-    initial_mode = initial_config["mode"]
-    
-    if initial_mode == "universal":
-        initial_kb_choices = list(KEYBOARD_MAP_UNIVERSAL.keys())
-        initial_mouse_choices = list(CAMERA_MAP_UNIVERSAL.keys())
-        initial_mouse_visible = True
-    elif initial_mode == "gta_drive":
-        initial_kb_choices = list(KEYBOARD_MAP_GTA.keys())
-        initial_mouse_choices = list(CAMERA_MAP_GTA.keys())
-        initial_mouse_visible = True
-    else:  # templerun
-        initial_kb_choices = list(KEYBOARD_MAP_TEMPLERUN.keys())
-        initial_mouse_choices = []
-        initial_mouse_visible = False
-    
-    theme = gr.themes.Base().set(
-        button_primary_background_fill="#2563eb",
-        button_primary_background_fill_hover="#1d4ed8",
-        button_primary_text_color="white",
-        slider_color="#2563eb",
-        checkbox_background_color_selected="#2563eb",
-    )
-    
-    with gr.Blocks(title="FastVideo - Matrix Game 2.0", theme=theme) as demo:
-        game_state = gr.State({
-            "initialized": False,
-            "current_model": None,
-            "block_idx": 0,
-            "max_blocks": 50,
-        })
-        
-        # Header
-        gr.Image("assets/full.svg", show_label=False, container=False, height=80)
-        
-        gr.HTML("""
-        <div style="text-align: center; margin-bottom: 10px;">
-            <p style="font-size: 18px;"> Make Video Generation Go Blurrrrrrr </p>
-            <p style="font-size: 18px;"> <a href="https://github.com/hao-ai-lab/FastVideo/tree/main" target="_blank">Code</a> | <a href="https://hao-ai-lab.github.io/blogs/fastvideo_post_training/" target="_blank">Blog</a> | <a href="https://hao-ai-lab.github.io/FastVideo/" target="_blank">Docs</a>  </p>
-        </div>
-        """)
-        
-        with gr.Accordion("🎥 What Is FastVideo?", open=False):
-            gr.HTML("""
-            <div style="padding: 20px; line-height: 1.6;">
-                <p style="font-size: 16px; margin-bottom: 15px;">
-                    FastVideo is an inference and post-training framework for diffusion models. It features an end-to-end unified pipeline for accelerating diffusion models, starting from data preprocessing to model training, finetuning, distillation, and inference. FastVideo is designed to be modular and extensible, allowing users to easily add new optimizations and techniques. Whether it is training-free optimizations or post-training optimizations, FastVideo has you covered.
-                </p>
-            </div>
-            """)
-        
-        # Model Selection
-        with gr.Row():
-            model_selection = gr.Dropdown(
-                choices=[loaded_model_name],
-                value=loaded_model_name,
-                label="Select Model",
-                interactive=False
-            )
-        
-
-        # Main Layout
-        with gr.Row(equal_height=True, elem_classes="main-content-row"):
-            with gr.Column(scale=1, elem_classes="advanced-options-column"):
-                with gr.Group():
-                    gr.HTML("<div style='margin: 0 0 15px 0; text-align: center; font-size: 16px;'>Game Controls</div>")
-                    
-                    with gr.Group():
-                        gr.HTML("<div style='font-size: 14px; margin-bottom: 5px; font-weight: bold;'>🎮 Keyboard Control</div>")
-                        keyboard_action = gr.Radio(
-                            choices=initial_kb_choices,
-                            value=initial_kb_choices[0] if initial_kb_choices else None,
-                            label="Movement",
-                            show_label=False,
-                            interactive=True
-                        )
-                    
-                    with gr.Group(visible=initial_mouse_visible) as mouse_group:
-                        gr.HTML("<div style='font-size: 14px; margin-bottom: 5px; font-weight: bold;'>🖱️ Mouse/Camera Control</div>")
-                        mouse_action = gr.Radio(
-                            choices=initial_mouse_choices if initial_mouse_visible else [],
-                            value=initial_mouse_choices[0] if initial_mouse_choices else None,
-                            label="Camera",
-                            show_label=False,
-                            interactive=True
-                        )
-                    
-                    with gr.Row():
-                        action_btn = gr.Button("Start", variant="primary")
-                        stop_btn = gr.Button("Stop", variant="stop")
-                    
-                    gr.HTML("<div style='margin-top: 15px;'></div>")
-                    
-                    seed = gr.Slider(
-                        label="Seed",
-                        minimum=0,
-                        maximum=1000000,
-                        step=1,
-                        value=1024,
-                    )
-                    randomize_seed = gr.Checkbox(label="Randomize seed", value=False)
-                    seed_output = gr.Number(label="Used Seed")
-                    
-                    block_counter = gr.Textbox(label="Progress", value="Block: 0 / 50", interactive=False, lines=1)
-
-
-            # Right Column: Video Output
-            with gr.Column(scale=1, elem_classes="video-column"):
-                video_output = gr.Video(
-                    label="Generated Video",
-                    show_label=True,
-                    height=466,
-                    width=600,
-                    container=True,
-                    elem_classes="video-component",
-                    autoplay=True
-                )
-
-        # Styles
-        gr.HTML("""
-        <style>
-        .center-button {
-            display: flex !important;
-            justify-content: center !important;
-            height: 100% !important;
-            padding-top: 1.4em !important;
-        }
-        
-        .gradio-container {
-            max-width: 1200px !important;
-            margin: 0 auto !important;
-        }
-        
-        .main {
-            max-width: 1200px !important;
-            margin: 0 auto !important;
-        }
-        
-        .gr-form, .gr-box, .gr-group {
-            max-width: 1200px !important;
-        }
-        
-        .gr-video {
-            max-width: 500px !important;
-            margin: 0 auto !important;
-        }
-        
-        .main-content-row {
-            display: flex !important;
-            align-items: flex-start !important;
-            min-height: 500px !important;
-            gap: 20px !important;
-        }
-        
-        .advanced-options-column,
-        .video-column {
-            display: flex !important;
-            flex-direction: column !important;
-            flex: 1 !important;
-            min-height: 400px !important;
-            align-items: stretch !important;
-        }
-        
-        .video-column > * {
-            margin-top: 0 !important;
-        }
-        
-        .video-column .gr-video,
-        .video-component {
-            margin-top: 0 !important;
-            padding-top: 0 !important;
-        }
-        
-        .video-column .gr-video .gr-form {
-            margin-top: 0 !important;
-        }
-        
-        .advanced-options-column .gr-group,
-        .video-column .gr-video {
-            margin-top: 0 !important;
-            vertical-align: top !important;
-        }
-        
-        .advanced-options-column > *:last-child,
-        .video-column > *:last-child {
-            flex-grow: 0 !important;
-        }
-        
-        @media (max-width: 1400px) {
-            .main-content-row {
-                min-height: 600px !important;
-            }
-            
-            .advanced-options-column,
-            .video-column {
-                min-height: 600px !important;
-            }
-        }
-        
-        @media (max-width: 1200px) {
-            .main-content-row {
-                flex-direction: column !important;
-                align-items: stretch !important;
-            }
-            
-            .advanced-options-column,
-            .video-column {
-                min-height: auto !important;
-                width: 100% !important;
-            }
-        }
-        
-        .timing-card {
-            background: var(--background-fill-secondary) !important;
-            border: 1px solid var(--border-color-primary) !important;
-            color: var(--body-text-color) !important;
-            padding: 10px;
-            border-radius: 8px;
-            text-align: center;
-            min-height: 80px;
-            display: flex;
-            flex-direction: column;
-            justify-content: center;
-        }
-        
-        .timing-card-highlight {
-            background: var(--background-fill-primary) !important;
-            border: 2px solid var(--color-accent) !important;
-        }
-        
-        .performance-card {
-            background: var(--background-fill-secondary) !important;
-            border: 1px solid var(--border-color-primary) !important;
-            color: var(--body-text-color) !important;
-            padding: 10px;
-            border-radius: 6px;
-            text-align: center;
-        }
-
-        .gr-number input[readonly] {
-            background-color: var(--background-fill-secondary) !important;
-            border: 1px solid var(--border-color-primary) !important;
-            color: var(--body-text-color-subdued) !important;
-            cursor: default !important;
-            text-align: center !important;
-            font-weight: 500 !important;
-        }
-        </style>
-        """)
-        
-        # UI update based on model selection
-        def on_model_change(model_name):
-            config = VARIANT_CONFIG.get(model_name, VARIANT_CONFIG["Matrix-Game-2.0-Base"])
-            mode = config["mode"]
-            
-            if mode == "universal":
-                kb_choices = list(KEYBOARD_MAP_UNIVERSAL.keys())
-                mouse_choices = list(CAMERA_MAP_UNIVERSAL.keys())
-                mouse_visible = True
-            elif mode == "gta_drive":
-                kb_choices = list(KEYBOARD_MAP_GTA.keys())
-                mouse_choices = list(CAMERA_MAP_GTA.keys())
-                mouse_visible = True
-            else:  # templerun
-                kb_choices = list(KEYBOARD_MAP_TEMPLERUN.keys())
-                mouse_choices = []
-                mouse_visible = False
-            
-            return (
-                gr.update(choices=kb_choices, value=kb_choices[0] if kb_choices else None),
-                gr.update(choices=mouse_choices, value=mouse_choices[0] if mouse_choices else None, visible=mouse_visible),
-                gr.update(visible=mouse_visible),
-            )
-        
-        model_selection.change(
-            fn=on_model_change,
-            inputs=model_selection,
-            outputs=[keyboard_action, mouse_action, mouse_group]
-        )
-
-        def start_game(model_name, seed_val, randomize, state):
-            if randomize:
-                seed_val = torch.randint(0, 1000000, (1,)).item()
-            
-            config = VARIANT_CONFIG.get(model_name)
-            if not config:
-                return state, seed_val, "Block: 0 / 50", None, "", gr.update(), gr.update()
-            
-            generator = generators.get(config["model_path"])
-            if not generator:
-                return state, seed_val, "Block: 0 / 50", None, "", gr.update(), gr.update()
-            
-            # If already initialized, clean up first
-            if state.get("initialized"):
-                try:
-                    # Clear accumulated frames without saving
-                    generator.accumulated_frames = []
-                    generator.executor.execute_streaming_clear()
-                except Exception as e:
-                    print(f"Warning: cleanup error: {e}")
-            
-            # Streaming parameters
-            num_latent_frames_per_block = 3
-            max_blocks = 50
-            total_latent_frames = num_latent_frames_per_block * max_blocks
-            num_frames = (total_latent_frames - 1) * 4 + 1
-            
-            actions = {
-                "keyboard": torch.zeros((num_frames, config["keyboard_dim"])),
-                "mouse": torch.zeros((num_frames, 2))
-            }
-            grid_sizes = torch.tensor([150, 44, 80])
-            
-            output_dir = os.path.abspath("outputs/matrixgame")
-            os.makedirs(output_dir, exist_ok=True)
-            video_path = os.path.join(output_dir, f"video_{int(time.time())}.mp4")
-            
-            generator.reset(
-                prompt="",
-                image_path=config["image_url"],
-                mouse_cond=actions["mouse"].unsqueeze(0),
-                keyboard_cond=actions["keyboard"].unsqueeze(0),
-                grid_sizes=grid_sizes,
-                num_frames=num_frames,
-                height=352,
-                width=640,
-                num_inference_steps=50,
-                output_path=video_path,
-            )
-            
-            new_state = {
-                "initialized": True,
-                "current_model": model_name,
-                "block_idx": 0,
-                "max_blocks": max_blocks,
-                "video_path": video_path,
-                "frames_per_block": num_latent_frames_per_block * 4,
-                "mode": config["mode"],
-                "seed": seed_val,
-            }
-            
-            return new_state, seed_val, "Block: 0 / 50", None, gr.update(value="Step"), gr.update(interactive=True)
-        
-        async def step_game(keyboard_key, mouse_key, model_name, state):
-            if not state.get("initialized"):
-                return state, state.get("seed", 0), "Block: 0 / 50", None, gr.update(), gr.update()
-            
-            # total_start_time = time.time()
-            config = VARIANT_CONFIG.get(model_name)
-            generator = generators.get(config["model_path"])
-            mode = state["mode"]
-            frames_per_block = state["frames_per_block"]
-
-            # Parse inputs to tensors
-            action = get_action_tensors(mode, keyboard_key, mouse_key)
-            keyboard_cond, mouse_cond = expand_action_to_frames(action, frames_per_block)
-            
-            # run step async
-            # inference_start_time = time.time()
-            frames, block_future = await generator.step_async(keyboard_cond, mouse_cond)
-            # inference_time = time.time() - inference_start_time
-            
-            # wait for block file to be written
-            block_path = await asyncio.to_thread(block_future.result) if block_future else None
-            state["block_idx"] = generator.block_idx
-            block_str = f"Block: {state['block_idx']} / {state['max_blocks']}"
-            
-            # total_time = time.time() - total_start_time
-            
-            # Timing breakdown
-            # timing_html = create_timing_display(inference_time, total_time, [], frames_per_block)
-
-            return state, state.get("seed", 0), block_str, block_path, gr.update(), gr.update()
-
-        def stop_game(model_name, state):
-            if not state.get("initialized"):
-                return {"initialized": False}, 0, "Block: 0 / 50", None, gr.update(value="Start"), gr.update(interactive=False)
-            
-            config = VARIANT_CONFIG.get(model_name)
-            generator = generators.get(config["model_path"])
-            
-            final_path = state.get("video_path")
-            generator.finalize(final_path)
-            
-            return {"initialized": False}, state.get("seed", 0), "Block: 0 / 50", final_path, gr.update(value="Start"), gr.update(interactive=False)
-        
-        async def handle_action(keyboard_key, mouse_key, model_name, seed_val, randomize, state):
-            if not state.get("initialized"):
-                return start_game(model_name, seed_val, randomize, state)
-            else:
-                return await step_game(keyboard_key, mouse_key, model_name, state)
-        
-        action_btn.click(
-            fn=handle_action,
-            inputs=[keyboard_action, mouse_action, model_selection, seed, randomize_seed, game_state],
-            outputs=[game_state, seed_output, block_counter, video_output, action_btn, stop_btn]
-        )
-        
-        stop_btn.click(
-            fn=stop_game,
-            inputs=[model_selection, game_state],
-            outputs=[game_state, seed_output, block_counter, video_output, action_btn, stop_btn]
-        )
-        
-        gr.HTML("""
-        <div style="text-align: center; margin-top: 10px; margin-bottom: 15px;">
-            <p style="font-size: 16px; margin: 0;">Note that this demo is meant to showcase Matrix Game's quality and that under a large number of requests, generation speed may be affected.</p>
-        </div>
-        """)
-    
-    return demo
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Matrix Game Gradio Demo")
-    parser.add_argument("--model", type=str, default="Matrix-Game-2.0-Base",
-                        choices=list(VARIANT_CONFIG.keys()),
-                        help="Model variant to load")
-    parser.add_argument("--host", type=str, default="0.0.0.0")
-    parser.add_argument("--port", type=int, default=7860)
-    args = parser.parse_args()
-    
-    # Load the selected model
-    config = VARIANT_CONFIG[args.model]
-    model_path = config["model_path"]
-    
-    print(f"Loading model: {model_path}")
-    setup_model_environment(model_path)
-    generator = StreamingVideoGenerator.from_pretrained(
-        model_path,
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        pin_cpu_memory=True,
-    )
-    
-    generators = {model_path: generator}
-    
-    demo = create_gradio_interface(generators, args.model)
-    
-    print(f"Starting Gradio at http://{args.host}:{args.port}")
-    
-    # FastAPI Wrapper
-    app = FastAPI()
-    
-    @app.get("/logo.png")
-    def get_logo():
-        return FileResponse(
-            "assets/full.svg",
-            media_type="image/svg+xml",
-            headers={
-                "Cache-Control": "public, max-age=3600",
-                "Access-Control-Allow-Origin": "*"
-            }
-        )
-
-    @app.get("/favicon.ico")
-    def get_favicon():
-        favicon_path = "assets/icon-simple.svg"
-        
-        if os.path.exists(favicon_path):
-            return FileResponse(
-                favicon_path, 
-                media_type="image/svg+xml",
-                headers={
-                    "Cache-Control": "public, max-age=3600",
-                    "Access-Control-Allow-Origin": "*"
-                }
-            )
-        else:
-            raise HTTPException(status_code=404, detail="Favicon not found")
-    
-    @app.get("/", response_class=HTMLResponse)
-    def index(request: Request):
-        base_url = str(request.base_url).rstrip('/')
-        return f"""
-        <!DOCTYPE html>
-        <html lang="en">
-        <head>
-            <meta charset="UTF-8" />
-            <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-            
-            <title>FastVideo - Matrix Game 2.0</title>
-            <meta name="title" content="MatrixGame2.0">
-            <meta name="description" content="Make video generation go blurrrrrrr">
-            <meta name="keywords" content="FastVideo, video generation, AI, machine learning, Matrix Game 2.0">
-            
-            <meta property="og:type" content="website">
-            <meta property="og:url" content="{base_url}/">
-            <meta property="og:title" content="FastVideo - Matrix Game 2.0">
-            <meta property="og:description" content="Make video generation go blurrrrrrr">
-            <meta property="og:image" content="{base_url}/logo.png">
-            <meta property="og:image:width" content="1200">
-            <meta property="og:image:height" content="630">
-            <meta property="og:site_name" content="MatrixGame2.0">
-            
-            <meta property="twitter:card" content="summary_large_image">
-            <meta property="twitter:url" content="{base_url}/">
-            <meta property="twitter:title" content="MatrixGame2.0">
-            <meta property="twitter:description" content="Make video generation go blurrrrrrr">
-            <meta property="twitter:image" content="{base_url}/logo.png">
-            <link rel="icon" type="image/png" sizes="32x32" href="/favicon.ico">
-            <link rel="icon" type="image/png" sizes="16x16" href="/favicon.ico">
-            <link rel="apple-touch-icon" href="/favicon.ico">
-            <style>
-                body, html {{
-                    margin: 0;
-                    padding: 0;
-                    height: 100%;
-                    overflow: hidden;
-                }}
-                iframe {{
-                    width: 100%;
-                    height: 100vh;
-                    border: none;
-                }}
-            </style>
-        </head>
-        <body>
-            <iframe src="/gradio" width="100%" height="100%" style="border: none;"></iframe>
-        </body>
-        </html>
-        """
-
-    app = gr.mount_gradio_app(
-        app, 
-        demo, 
-        path="/gradio",
-        allowed_paths=[os.path.abspath("outputs"), os.path.abspath("fastvideo-logos")]
-    )
-    
-    uvicorn.run(app, host=args.host, port=args.port)
-
-
-if __name__ == "__main__":
-    main()
@@ -1,46 +0,0 @@
-from fastvideo import VideoGenerator
-import argparse
-
-OUTPUT_PATH = "video_samples_wan2_2_5B_ti2v"
-
-
-def main(text_encoder_path: str):
-    # FastVideo will automatically use the optimal default arguments for the
-    # model.
-    # If a local path is provided, FastVideo will make a best effort
-    # attempt to identify the optimal arguments.
-    model_name = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
-    generator = VideoGenerator.from_pretrained(
-        model_name,
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=False,
-        # AbsMaxFP8 is the quantization method used by ComfyUI; 
-        # check fastvideo/layers/quantization/* for more quantization methods
-        override_text_encoder_quant="AbsMaxFP8",
-        # for Wan 2.2, this is the path to "umt5_xxl_fp8_e4m3fn_scaled.safetensors"
-        override_text_encoder_safetensors=text_encoder_path,
-        pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-    )
-
-    # I2V is triggered just by passing in an image_path argument
-    prompt = "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
-    image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
-    video = generator.generate_video(
-        prompt, output_path=OUTPUT_PATH, save_video=True, image_path=image_path
-    )
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--text_encoder_path",
-        type=str,
-        required=True,
-        help="Path to the quantized text encoder safetensors file.",
-    )
-    args = parser.parse_args()
-    main(args.text_encoder_path)
@@ -1,93 +0,0 @@
-#!/bin/bash
-
-export WANDB_BASE_URL="https://api.wandb.ai"
-export WANDB_MODE=online
-export TOKENIZERS_PARALLELISM=false
-# export FASTVIDEO_ATTENTION_BACKEND=TORCH_SDPA
-
-MODEL_PATH="FastVideo/Matrix-Game-2.0-Foundation-Diffusers"
-DATA_DIR="footsies-dataset/preprocessed/combined_parquet_dataset"
-VALIDATION_DATASET_FILE="$(dirname "$0")/validation.json"
-NUM_GPUS=8
-# export CUDA_VISIBLE_DEVICES=4,5
-# IP=[MASTER NODE IP]
-
-# Training arguments
-training_args=(
-  --tracker_project_name "matrixgame_finetune"
-  --output_dir "checkpoints/matrixgame_finetune"
-  --max_train_steps 1500
-  --train_batch_size 1
-  --train_sp_batch_size 1
-  --gradient_accumulation_steps 4
-  --num_latent_t 20
-  --num_height 352
-  --num_width 640
-  --num_frames 77
-  --enable_gradient_checkpointing_type "full"
-)
-
-# Parallel arguments
-parallel_args=(
-  --num_gpus $NUM_GPUS
-  --sp_size 2
-  --tp_size 1
-  --hsdp_replicate_dim 4
-  --hsdp_shard_dim 2
-)
-
-# Model arguments
-model_args=(
-  --model_path $MODEL_PATH
-  --pretrained_model_name_or_path $MODEL_PATH
-)
-
-# Dataset arguments
-dataset_args=(
-  --data_path "$DATA_DIR"
-  --dataloader_num_workers 1
-)
-
-# Validation arguments
-validation_args=(
-  --log_validation
-  --validation_dataset_file "$VALIDATION_DATASET_FILE"
-  --validation_steps 100
-  --validation_sampling_steps "40"
-  --validation_guidance_scale "6.0"
-)
-
-# Optimizer arguments
-optimizer_args=(
-  --learning_rate 2e-5
-  --mixed_precision "bf16"
-  --weight_only_checkpointing_steps 100
-  --training_state_checkpointing_steps 100
-  --weight_decay 1e-4
-  --max_grad_norm 1.0
-)
-
-# Miscellaneous arguments
-miscellaneous_args=(
-  --inference_mode False
-  --checkpoints_total_limit 3
-  --training_cfg_rate 0.1
-  --multi_phased_distill_schedule "4000-1"
-  --not_apply_cfg_solver
-  --dit_precision "fp32"
-  --num_euler_timesteps 50
-  --ema_start_step 0
-)
-
-# If you do not have 32 GPUs and to fit in memory, you can: 1. increase sp_size. 2. reduce num_latent_t
-torchrun \
-  --nnodes 1 \
-  --nproc_per_node $NUM_GPUS \
-    fastvideo/training/matrixgame_training_pipeline.py \
-    "${parallel_args[@]}" \
-    "${model_args[@]}" \
-    "${dataset_args[@]}" \
-    "${training_args[@]}" \
-    "${optimizer_args[@]}" \
-    "${validation_args[@]}" \
-    "${miscellaneous_args[@]}"
@@ -1,27 +0,0 @@
-#!/bin/bash
-
-GPU_NUM=1 # 2,4,8
-MODEL_PATH="Matrix-Game-2.0-Foundation-Diffusers"
-DATA_MERGE_PATH="footsies-dataset/merge.txt"
-OUTPUT_DIR="footsies-dataset/preprocessed/"
-
-# export CUDA_VISIBLE_DEVICES=0
-export MASTER_ADDR=localhost
-export MASTER_PORT=29500
-export RANK=0
-export WORLD_SIZE=1
-
-python fastvideo/pipelines/preprocess/v1_preprocess.py \
-    --model_path $MODEL_PATH \
-    --data_merge_path $DATA_MERGE_PATH \
-    --preprocess_video_batch_size 4 \
-    --seed 42 \
-    --max_height 352 \
-    --max_width 640 \
-    --num_frames 77 \
-    --dataloader_num_workers 0 \
-    --output_dir=$OUTPUT_DIR \
-    --samples_per_file 4 \
-    --train_fps 25 \
-    --flush_frequency 4 \
-    --preprocess_task matrixgame
@@ -10,8 +10,6 @@ if(GPU_BACKEND STREQUAL "ROCM")
    enable_language(HIP)
 else()
    enable_language(CUDA)
-    # Ensure CUDA toolkit targets (CUDA::cudart, CUDA::cuda_driver, etc.) are available.
-    find_package(CUDAToolkit REQUIRED)
 endif()

 # Import common utils if needed, but we keep it simple for now
@@ -155,30 +153,6 @@ if(BUILD_CXX_KERNELS)
        $<$<COMPILE_LANGUAGE:CUDA>:${CUDA_FLAGS}>
    )

-    # Link against Torch libraries to avoid undefined symbols at import time
-    # (e.g., torch::autograd vtables) when loading the extension module.
-    target_link_libraries(fastvideo_kernel_ops PRIVATE ${TORCH_LIBRARIES})
-
-    # Also link against libtorch_python to satisfy Python-binding symbols
-    # (e.g., torch::PyWarningHandler) required by torch/extension.h.
-    execute_process(
-        COMMAND "${Python_EXECUTABLE}" -c "import torch; from pathlib import Path; p=Path(torch.__file__).parent/'lib'; m=sorted(p.glob('libtorch_python*')); print(str(m[0]) if m else '')"
-        OUTPUT_VARIABLE TORCH_PYTHON_LIBRARY_PATH
-        OUTPUT_STRIP_TRAILING_WHITESPACE
-        ERROR_QUIET
-    )
-    if(TORCH_PYTHON_LIBRARY_PATH)
-        message(STATUS "TORCH_PYTHON_LIBRARY_PATH: ${TORCH_PYTHON_LIBRARY_PATH}")
-        target_link_libraries(fastvideo_kernel_ops PRIVATE "${TORCH_PYTHON_LIBRARY_PATH}")
-    else()
-        message(WARNING "Could not locate libtorch_python; fastvideo_kernel_ops may fail to import.")
-    endif()
-
-    # Link CUDA runtime + driver explicitly (fixes missing symbols like cuGetErrorString at import time)
-    if(NOT GPU_BACKEND STREQUAL "ROCM")
-        target_link_libraries(fastvideo_kernel_ops PRIVATE CUDA::cudart CUDA::cuda_driver)
-    endif()
-
    # We install it to fastvideo_kernel/_C so we can load it to register the ops
    install(TARGETS fastvideo_kernel_ops LIBRARY DESTINATION fastvideo_kernel/_C)
 endif()
@@ -34,23 +34,12 @@ from fastvideo_kernel import sliding_tile_attention, video_sparse_attn, moba_att
 out = sliding_tile_attention(q, k, v, window_sizes, text_len)

 # Example: Video Sparse Attention (with Triton fallback)
-out = video_sparse_attn(q, k, v, block_sizes, block_sizes, topk=5)
+out = video_sparse_attn(q, k, v, block_sizes, topk=5)

 # Example: VMoBA
 out = moba_attn_varlen(q, k, v, cu_seqlens_q, cu_seqlens_k, ...)
 ```

-## Benchmark
-
-### VSA (block-sparse) TFLOPs
-
-After building/installing `fastvideo-kernel`, run:
-
-```bash
-cd fastvideo-kernel
-python benchmarks/bench_vsa.py --batch_size 1 --num_heads 16 --head_dim 128 --q_seq_lens 49152 --topk 64
-```
-
 ### TurboDiffusion Kernels

 This package also includes kernels from [TurboDiffusion](https://github.com/thu-ml/TurboDiffusion), including INT8 GEMM, Quantization, RMSNorm and LayerNorm.
@@ -1,166 +0,0 @@
-#!/usr/bin/env python3
-"""
-Benchmark VSA *wrapper* performance (forward + backward) and report TFLOPs.
-
-This script benchmarks the autograd-enabled wrapper:
-  - fastvideo_kernel.block_sparse_attn.block_sparse_attn
-
-So measured time includes wrapper overhead (map->index conversion, dispatch) plus kernel time.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import random
-from typing import Tuple, Callable
-
-import numpy as np
-import torch
-
-try:
-    from triton.testing import do_bench
-except Exception as e:  # pragma: no cover
-    raise ImportError("This benchmark requires triton (for triton.testing.do_bench).") from e
-
-
-BLOCK_M = 64
-BLOCK_N = 64
-
-
-def set_seed(seed: int = 42) -> None:
-    random.seed(seed)
-    np.random.seed(seed)
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-
-
-def parse_arguments() -> argparse.Namespace:
-    p = argparse.ArgumentParser(description="Benchmark FastVideo VSA block-sparse attention")
-    p.add_argument("--batch_size", type=int, default=1)
-    p.add_argument("--num_heads", type=int, default=12)
-    p.add_argument("--head_dim", type=int, default=128, choices=[64, 128])
-    p.add_argument("--topk", type=int, default=None, help="KV blocks per Q block (default: ~90%% sparsity)")
-    p.add_argument("--q_seq_lens", type=int, nargs="+", default=[49152], help="Q sequence lengths (must be /64)")
-    p.add_argument("--kv_seq_lens", type=int, nargs="+", default=None, help="KV sequence lengths (defaults to q_seq_len)")
-    p.add_argument("--warmup", type=int, default=5)
-    p.add_argument("--rep", type=int, default=20)
-    p.add_argument("--seed", type=int, default=42)
-    p.add_argument("--dtype", type=str, default="bf16", choices=["bf16", "fp16"])
-    p.add_argument("--force_triton", action="store_true", help="Force wrapper to use Triton path (if supported by shapes).")
-    return p.parse_args()
-
-
-def create_qkv(batch: int, heads: int, q_len: int, kv_len: int, d: int, dtype: torch.dtype) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    q = torch.randn(batch, heads, q_len, d, dtype=dtype, device="cuda")
-    k = torch.randn(batch, heads, kv_len, d, dtype=dtype, device="cuda")
-    v = torch.randn(batch, heads, kv_len, d, dtype=dtype, device="cuda")
-    return q, k, v
-
-
-def make_block_map(bs: int, h: int, num_q_blocks: int, num_kv_blocks: int, topk: int) -> torch.Tensor:
-    # block_map: [bs, h, num_q_blocks, num_kv_blocks] bool
-    scores = torch.rand(bs, h, num_q_blocks, num_kv_blocks, device="cuda")
-    topk = min(max(1, topk), num_kv_blocks)
-    idx = torch.topk(scores, topk, dim=-1).indices
-    block_map = torch.zeros(bs, h, num_q_blocks, num_kv_blocks, dtype=torch.bool, device="cuda")
-    block_map.scatter_(-1, idx, True)
-    return block_map
-
-
-def flops_sparse_attention(bs: int, h: int, d: int, q_len: int, topk_blocks: int, block_n: int) -> float:
-    # Approx: QK^T + PV, each is ~2*bs*h*q_len*(topk_blocks*block_n)*d
-    return 4.0 * bs * h * d * q_len * (topk_blocks * block_n)
-
-
-def bench_ms(fn: Callable[[], object], warmup: int, rep: int) -> float:
-    return do_bench(fn, warmup=warmup, rep=rep, quantiles=None)
-
-
-def main() -> None:
-    args = parse_arguments()
-    set_seed(args.seed)
-
-    dtype = torch.bfloat16 if args.dtype == "bf16" else torch.float16
-
-    if args.force_triton:
-        os.environ["FASTVIDEO_KERNEL_VSA_FORCE_TRITON"] = "1"
-
-    from fastvideo_kernel.block_sparse_attn import block_sparse_attn
-
-    bs, h, d = args.batch_size, args.num_heads, args.head_dim
-    kv_seq_lens = args.kv_seq_lens
-    if kv_seq_lens is None:
-        kv_seq_lens = args.q_seq_lens
-    if len(kv_seq_lens) != len(args.q_seq_lens):
-        raise ValueError("kv_seq_lens must have the same number of entries as q_seq_lens (or be omitted).")
-
-    print("VSA Block-Sparse Attention Benchmark (WRAPPER)")
-    print(f"device: {torch.cuda.get_device_name(0)}")
-    print(f"batch={bs}, heads={h}, head_dim={d}, dtype={args.dtype}")
-    print(f"BLOCK_M={BLOCK_M}, BLOCK_N={BLOCK_N}")
-    print("NOTE: timings include wrapper overhead (map->index + dispatch).")
-    if args.force_triton:
-        print("dispatch: forced Triton (FASTVIDEO_KERNEL_VSA_FORCE_TRITON=1)")
-    else:
-        print("dispatch: SM90 if available, else Triton")
-
-    for q_len, kv_len in zip(args.q_seq_lens, kv_seq_lens):
-        if q_len % BLOCK_M != 0 or kv_len % BLOCK_N != 0:
-            print(f"[skip] q_len={q_len}, kv_len={kv_len} must be divisible by 64")
-            continue
-
-        num_q_blocks = q_len // BLOCK_M
-        num_kv_blocks = kv_len // BLOCK_N
-        topk = args.topk if args.topk is not None else max(1, num_kv_blocks // 10)
-        topk = min(topk, num_kv_blocks)
-
-        print("\n" + "=" * 80)
-        print(f"q_len={q_len}, kv_len={kv_len}, num_q_blocks={num_q_blocks}, num_kv_blocks={num_kv_blocks}, topk={topk}")
-
-        q, k, v = create_qkv(bs, h, q_len, kv_len, d, dtype)
-        block_map = make_block_map(bs, h, num_q_blocks, num_kv_blocks, topk)
-
-        # Variable block sizes: default full blocks (64 tokens per KV block)
-        variable_block_sizes = torch.full((num_kv_blocks,), BLOCK_N, dtype=torch.int32, device="cuda")
-
-        def _fwd():
-            return block_sparse_attn(q, k, v, block_map, variable_block_sizes)
-
-        fwd_ms = bench_ms(_fwd, warmup=args.warmup, rep=args.rep)
-
-        # Backward benchmark (wrapper autograd). We build the graph once, then repeatedly run backward
-        # on the retained graph so bwd timing excludes the forward compute.
-        q_ = q.detach().requires_grad_(True)
-        k_ = k.detach().requires_grad_(True)
-        v_ = v.detach().requires_grad_(True)
-        o_, _aux_ = block_sparse_attn(q_, k_, v_, block_map, variable_block_sizes)
-        og = torch.randn_like(o_)
-        loss = (o_ * og).sum()
-
-        for _ in range(max(1, args.warmup // 2)):
-            torch.autograd.grad(loss, (q_, k_, v_), retain_graph=True)
-        torch.cuda.synchronize()
-
-        bwd_ms = bench_ms(
-            lambda: torch.autograd.grad(loss, (q_, k_, v_), retain_graph=True),
-            warmup=0,
-            rep=max(5, args.rep // 2),
-        )
-
-        flops = flops_sparse_attention(bs, h, d, q_len, topk, BLOCK_N)
-        fwd_tflops = flops / fwd_ms * 1e-12 * 1e3
-        # Rough backward multiplier (attention backward typically ~2-3x forward)
-        bwd_tflops = (2.5 * flops) / bwd_ms * 1e-12 * 1e3
-
-        print(f"fwd(wrapper): {fwd_ms:.3f} ms  | {fwd_tflops:.2f} TFLOPs (approx)")
-        print(f"bwd(wrapper): {bwd_ms:.3f} ms  | {bwd_tflops:.2f} TFLOPs (approx)")
-
-
-if __name__ == "__main__":
-    if not torch.cuda.is_available():
-        raise RuntimeError("CUDA is required for this benchmark.")
-    main()
-
-
@@ -639,8 +639,7 @@ void bwd_attend_ker(const __grid_constant__ bwd_globals<D> g) {

    // store kq and vq

-    // ! the following two line seems unnecessary.
-    // tma::store_async_wait(); // ensure qg is finished
+    // ensuring all writes are finished
    __syncthreads();

    warpgroup::store(kg_smem[0], kg_reg);
@@ -661,6 +660,145 @@ void bwd_attend_ker(const __grid_constant__ bwd_globals<D> g) {
    tma::store_async_wait(); 
 }

+
+template<int D>
+void block_sparse_attention_forward_impl(
+    bf16* d_q, bf16* d_k, bf16* d_v, float* d_l, bf16* d_o,
+    int batch, int qo_heads, int kv_heads, int seq_len, int hr,
+    int max_kv_blocks_per_q, 
+    int32_t* q2k_block_sparse_index_ptr,
+    int32_t* q2k_block_sparse_num_ptr,
+    int32_t* block_size_ptr,
+    cudaStream_t stream
+) {
+    using K = fwd_attend_ker_tile_dims<D>;
+    using q_tile    =         st_bf<K::qo_height, K::tile_width>;
+    using k_tile    =         st_bf<K::kv_height, K::tile_width>;
+    using v_tile    =         st_bf<K::kv_height, K::tile_width>;
+    using l_col_vec = col_vec<st_fl<K::qo_height, K::tile_width>>;
+    using o_tile    =         st_bf<K::qo_height, K::tile_width>;
+
+    using q_global = gl<bf16,  -1, -1, -1, -1, q_tile>;
+    using k_global = gl<bf16,  -1, -1, -1, -1, k_tile>;
+    using v_global = gl<bf16,  -1, -1, -1, -1, v_tile>;
+    using l_global = gl<float, -1, -1, -1, -1, l_col_vec>;
+    using o_global = gl<bf16,  -1, -1, -1, -1, o_tile>;
+
+    using globals      = fwd_globals<D>;
+
+    q_global qg_arg{d_q, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    k_global kg_arg{d_k, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    v_global vg_arg{d_v, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    l_global lg_arg{d_l, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,   static_cast<unsigned int>(seq_len)};
+    o_global og_arg{d_o, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+
+    globals g{
+        qg_arg, kg_arg, vg_arg, lg_arg, og_arg, 
+        static_cast<int>(seq_len), static_cast<int>(hr), static_cast<int>(max_kv_blocks_per_q), 
+        q2k_block_sparse_index_ptr, q2k_block_sparse_num_ptr, block_size_ptr
+    };
+
+    // Shared memory size for the kernel
+    // 54000 bytes is calibrated for H100 shared memory constraints for these tile sizes
+    constexpr int mem_size = 54000;
+
+    dim3 grid(seq_len/(64), qo_heads, batch);
+
+    cudaFuncSetAttribute(
+        fwd_attend_ker<D>,
+        cudaFuncAttributeMaxDynamicSharedMemorySize,
+        mem_size
+    );
+
+    fwd_attend_ker<D><<<grid, (128), mem_size, stream>>>(g);
+}
+
+template<int D>
+void block_sparse_attention_backward_impl(
+    bf16* d_q, bf16* d_k, bf16* d_v, bf16* d_o, bf16* d_og, float* d_l, float* d_d, float* d_qg, float* d_kg, float* d_vg,
+    int batch, int qo_heads, int kv_heads, int seq_len, int hr, int max_q_blocks_per_kv,
+    int32_t* k2q_block_sparse_index_ptr,
+    int32_t* k2q_block_sparse_num_ptr,
+    int32_t* block_size_ptr,
+    cudaStream_t stream
+) {
+    using G = bwd_attend_ker_tile_dims<D>;
+    using og_tile = st_bf<4*16, D>;
+    using o_tile  = st_bf<4*16, D>;
+    using d_tile  = col_vec<st_fl<4*16, D>>;
+
+    using og_global = gl<bf16,  -1, -1, -1, -1, og_tile>;
+    using o_global  = gl<bf16,  -1, -1, -1, -1, o_tile>;
+    using d_global  = gl<float, -1, -1, -1, -1, d_tile>;
+
+    using prep_globals = bwd_prep_globals<D>;
+
+    constexpr int mem_size_prep = kittens::MAX_SHARED_MEMORY;
+    int threads_prep = PREP_NUM_WARPS * kittens::WARP_THREADS;
+    dim3 grid_bwd_prep(seq_len/(PREP_NUM_WARPS*kittens::TILE_ROW_DIM<bf16>*4), qo_heads, batch);
+
+    og_global prep_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    o_global  prep_o_arg {d_o,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    d_global  prep_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};
+
+    prep_globals bwd_g{prep_og_arg, prep_o_arg, prep_d_arg};
+
+    cudaFuncSetAttribute(
+        bwd_attend_prep_ker<D>,
+        cudaFuncAttributeMaxDynamicSharedMemorySize,
+        mem_size_prep
+    );
+    bwd_attend_prep_ker<D><<<grid_bwd_prep, threads_prep, mem_size_prep, stream>>>(bwd_g);
+
+    using bwd_q_tile    =         st_bf<G::tile_h_qo, G::tile_width>;
+    using bwd_k_tile    =         st_bf<G::tile_h,    G::tile_width>;
+    using bwd_v_tile    =         st_bf<G::tile_h,    G::tile_width>;
+    using bwd_og_tile   =         st_bf<G::tile_h_qo, G::tile_width>;
+    using bwd_qg_tile   =         st_fl<G::tile_h_qo, G::tile_width>;
+    using bwd_kg_tile   =         st_fl<G::tile_h,    G::tile_width>;
+    using bwd_vg_tile   =         st_fl<G::tile_h,    G::tile_width>;
+    using bwd_l_tile    = row_vec<st_fl<G::tile_h_qo, G::tile_h>>;
+    using bwd_d_tile    = row_vec<st_fl<G::tile_h_qo, G::tile_h>>;
+
+    using bwd_q_global  = gl<bf16,  -1, -1, -1, -1, bwd_q_tile>;
+    using bwd_k_global  = gl<bf16,  -1, -1, -1, -1, bwd_k_tile>;
+    using bwd_v_global  = gl<bf16,  -1, -1, -1, -1, bwd_v_tile>;
+    using bwd_og_global = gl<bf16,  -1, -1, -1, -1, bwd_og_tile>;
+    using bwd_qg_global = gl<float, -1, -1, -1, -1, bwd_qg_tile>;
+    using bwd_kg_global = gl<float, -1, -1, -1, -1, bwd_kg_tile>;
+    using bwd_vg_global = gl<float, -1, -1, -1, -1, bwd_vg_tile>;
+    using bwd_l_global  = gl<float, -1, -1, -1, -1, bwd_l_tile>;
+    using bwd_d_global  = gl<float, -1, -1, -1, -1, bwd_d_tile>;
+
+    using bwd_global_args = bwd_globals<D>;
+
+    bwd_q_global  bwd_q_arg {d_q,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_k_global  bwd_k_arg {d_k,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_v_global  bwd_v_arg {d_v,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_og_global bwd_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_qg_global bwd_qg_arg{d_qg, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_kg_global bwd_kg_arg{d_kg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_vg_global bwd_vg_arg{d_vg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), static_cast<uint32_t>(D)};
+    bwd_l_global  bwd_l_arg {d_l,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};
+    bwd_d_global  bwd_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};
+
+    bwd_global_args bwd_global{bwd_q_arg, bwd_k_arg, bwd_v_arg, bwd_og_arg, bwd_qg_arg, bwd_kg_arg, bwd_vg_arg, bwd_l_arg, bwd_d_arg, 
+                        static_cast<int>(seq_len), static_cast<int>(hr), static_cast<int>(max_q_blocks_per_kv),
+                        k2q_block_sparse_index_ptr, k2q_block_sparse_num_ptr, block_size_ptr};
+
+    dim3 grid_bwd_main(seq_len/64, qo_heads, batch);
+    int threads_main = 128;
+    // Calibrated shared memory sizes for different head dimensions
+    int bwd_mem_size = (D == 64) ? 72000 : 113000;
+
+    cudaFuncSetAttribute(
+        bwd_attend_ker<D>,
+        cudaFuncAttributeMaxDynamicSharedMemorySize,
+        bwd_mem_size
+    );
+    bwd_attend_ker<D><<<grid_bwd_main, threads_main, bwd_mem_size, stream>>>(bwd_global);
+}
+
 #include "pyutils/torch_helpers.cuh"
 #include <ATen/cuda/CUDAContext.h>
 #include <iostream>
@@ -672,32 +810,23 @@ block_sparse_attention_forward(
    torch::Tensor v, 
    torch::Tensor q2k_block_sparse_index, 
    torch::Tensor q2k_block_sparse_num, 
-    torch::Tensor kv_block_size
+    torch::Tensor block_size
 )
 {
    CHECK_INPUT(q);
    CHECK_INPUT(k);
    CHECK_INPUT(v);

-    // q shape: (batch, qo_heads, q_seq_len, head_dim)
-    // k shape: (batch, kv_heads, kv_seq_len, head_dim)
-    // v shape: (batch, kv_heads, kv_seq_len, head_dim)
-    // q2k_block_sparse_index shape: (batch, qo_heads, num_q_blocks, max_kv_blocks_per_q)
-    // q2k_block_sparse_num shape: (batch, qo_heads, num_q_blocks)
-    // kv_block_size shape: (num_kv_blocks) This does not need other dimensions because across all batch/heads the padding is the same.
-    
    auto batch    = q.size(0);
-    auto q_seq_len  = q.size(2);
-    auto kv_seq_len = k.size(2);
+    auto seq_len  = q.size(2); 
    auto head_dim = q.size(3); 
    auto qo_heads = q.size(1);
    auto kv_heads = k.size(1);
    auto max_kv_blocks_per_q = q2k_block_sparse_index.size(3);
-    auto num_q_blocks = q2k_block_sparse_index.size(2);
-    auto num_kv_blocks = kv_block_size.size(0);
+    auto num_q_blocks = block_size.size(0);
    TORCH_CHECK(batch==1, "Batch size dim will be removed in the future, please set batch to 1");
-    TORCH_CHECK(num_q_blocks * BLOCK_M == q_seq_len, "This kernel supports variable q block size, but it assumes the input sequence is properly padded.");
-    TORCH_CHECK(num_kv_blocks * BLOCK_M == kv_seq_len, "This kernel supports variable kv block size, but it assumes the input sequence is properly padded.");
+    TORCH_CHECK(num_q_blocks * 64 == seq_len, "This kernel supports variable block size, but it assumes the input sequence is properly padded.");
+    TORCH_CHECK(num_q_blocks == q2k_block_sparse_index.size(2), "Number of Q blocks does not match between q2k_block_sparse_index and block_size");
    // check to see that these dimensions match for all inputs
    TORCH_CHECK(q.size(0) == batch, "Q batch dimension - idx 0 - must match for all inputs");
    TORCH_CHECK(k.size(0) == batch, "K batch dimension - idx 0 - must match for all inputs");
@@ -705,9 +834,11 @@ block_sparse_attention_forward(
    TORCH_CHECK(q2k_block_sparse_index.size(0) == batch, "q2k_block_sparse_index batch dimension - idx 0 - must match for all inputs");
    TORCH_CHECK(q2k_block_sparse_num.size(0) == batch, "q2k_block_sparse_num batch dimension - idx 0 - must match for all inputs");

-    TORCH_CHECK(v.size(2) == kv_seq_len, "V sequence length dimension - idx 2 - must match K inputs");
-    TORCH_CHECK(q2k_block_sparse_num.size(2) == num_q_blocks, "q2k_block_sparse_num idx 2 - must match num_q_blocks");
-
+    TORCH_CHECK(q.size(2) == seq_len, "Q sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(k.size(2) == seq_len, "K sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(v.size(2) == seq_len, "V sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(q2k_block_sparse_index.size(2) == seq_len / BLOCK_M, "q2k_block_sparse_index idx 2 - must match seq_len / BLOCK_M");
+    TORCH_CHECK(q2k_block_sparse_num.size(2) == seq_len / BLOCK_M, "q2k_block_sparse_num idx 2 - must match seq_len / BLOCK_M");

    TORCH_CHECK(q.size(3) == head_dim, "Q head dimension - idx 3 - must match for all non-vector inputs");
    TORCH_CHECK(k.size(3) == head_dim, "K head dimension - idx 3 - must match for all non-vector inputs");
@@ -733,12 +864,12 @@ block_sparse_attention_forward(
    // for the returned outputs
    torch::Tensor o     = torch::empty({static_cast<const uint>(batch), 
                                        static_cast<const uint>(qo_heads), 
-                                        static_cast<const uint>(q_seq_len), 
+                                        static_cast<const uint>(seq_len), 
                                        static_cast<const uint>(head_dim)}, v.options());
    
    torch::Tensor l_vec = torch::empty({static_cast<const uint>(batch), 
                                        static_cast<const uint>(qo_heads), 
-                                        static_cast<const uint>(q_seq_len), 
+                                        static_cast<const uint>(seq_len), 
                                        static_cast<const uint>(1)}, 
                                        torch::TensorOptions().dtype(torch::kFloat).device(q.device()).memory_format(at::MemoryFormat::Contiguous));
        
@@ -749,110 +880,32 @@ block_sparse_attention_forward(
    float* l_ptr = reinterpret_cast<float*>(l_vec.data_ptr<float>());
    float* d_l   = reinterpret_cast<float*>(l_ptr);

-    //cudadevicesynchronize();
    const c10::cuda::OptionalCUDAGuard device_guard(q.device());    
    const cudaStream_t stream = at::cuda::getCurrentCUDAStream().stream(); 

+    // Temporated implementation to avoid code duplication between head_dim=64 and 128
    if (head_dim == 64) {
-        using q_tile    =         st_bf<fwd_attend_ker_tile_dims<64>::qo_height, fwd_attend_ker_tile_dims<64>::tile_width>;
-        using k_tile    =         st_bf<fwd_attend_ker_tile_dims<64>::kv_height, fwd_attend_ker_tile_dims<64>::tile_width>;
-        using v_tile    =         st_bf<fwd_attend_ker_tile_dims<64>::kv_height, fwd_attend_ker_tile_dims<64>::tile_width>;
-        using l_col_vec = col_vec<st_fl<fwd_attend_ker_tile_dims<64>::qo_height, fwd_attend_ker_tile_dims<64>::tile_width>>;
-        using o_tile    =         st_bf<fwd_attend_ker_tile_dims<64>::qo_height, fwd_attend_ker_tile_dims<64>::tile_width>;
-
-        using q_global = gl<bf16,  -1, -1, -1, -1, q_tile>;
-        using k_global = gl<bf16,  -1, -1, -1, -1, k_tile>;
-        using v_global = gl<bf16,  -1, -1, -1, -1, v_tile>;
-        using l_global = gl<float, -1, -1, -1, -1, l_col_vec>;
-        using o_global = gl<bf16,  -1, -1, -1, -1, o_tile>;
-
-        using globals      = fwd_globals<64>;
-
-        q_global qg_arg{d_q, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        k_global kg_arg{d_k, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        v_global vg_arg{d_v, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        l_global lg_arg{d_l, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,   static_cast<unsigned int>(q_seq_len)};
-        o_global og_arg{d_o, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-
-        globals g{
-            qg_arg, 
-            kg_arg, 
-            vg_arg, 
-            lg_arg, 
-            og_arg, 
-            static_cast<int>(q_seq_len), 
-            static_cast<int>(hr), 
-            static_cast<int>(max_kv_blocks_per_q), 
-            reinterpret_cast<int32_t*>(q2k_block_sparse_index.data_ptr()), 
+        block_sparse_attention_forward_impl<64>(
+            d_q, d_k, d_v, d_l, d_o,
+            batch, qo_heads, kv_heads, seq_len, hr,
+            max_kv_blocks_per_q,
+            reinterpret_cast<int32_t*>(q2k_block_sparse_index.data_ptr()),
            reinterpret_cast<int32_t*>(q2k_block_sparse_num.data_ptr()),
-            reinterpret_cast<int32_t*>(kv_block_size.data_ptr())
-        };
-
-        constexpr int mem_size = 54000;
-
-        dim3 grid(q_seq_len/(BLOCK_M), qo_heads, batch);
-
-        cudaFuncSetAttribute(
-            fwd_attend_ker<64>,
-            cudaFuncAttributeMaxDynamicSharedMemorySize,
-            mem_size
+            reinterpret_cast<int32_t*>(block_size.data_ptr()),
+            stream
        );
-
-        fwd_attend_ker<64><<<grid, (128), mem_size, stream>>>(g);
-
-        CHECK_CUDA_ERROR(cudaGetLastError());
-        // cudaStreamSynchronize(stream);
-    }
-
-    if (head_dim == 128) {
-        using q_tile    =         st_bf<fwd_attend_ker_tile_dims<128>::qo_height, fwd_attend_ker_tile_dims<128>::tile_width>;
-        using k_tile    =         st_bf<fwd_attend_ker_tile_dims<128>::kv_height, fwd_attend_ker_tile_dims<128>::tile_width>;
-        using v_tile    =         st_bf<fwd_attend_ker_tile_dims<128>::kv_height, fwd_attend_ker_tile_dims<128>::tile_width>;
-        using l_col_vec = col_vec<st_fl<fwd_attend_ker_tile_dims<128>::qo_height, fwd_attend_ker_tile_dims<128>::tile_width>>;
-        using o_tile    =         st_bf<fwd_attend_ker_tile_dims<128>::qo_height, fwd_attend_ker_tile_dims<128>::tile_width>;
-
-        using q_global = gl<bf16,  -1, -1, -1, -1, q_tile>;
-        using k_global = gl<bf16,  -1, -1, -1, -1, k_tile>;
-        using v_global = gl<bf16,  -1, -1, -1, -1, v_tile>;
-        using l_global = gl<float, -1, -1, -1, -1, l_col_vec>;
-        using o_global = gl<bf16,  -1, -1, -1, -1, o_tile>;
-
-        using globals      = fwd_globals<128>;
-
-        q_global qg_arg{d_q, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        k_global kg_arg{d_k, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        v_global vg_arg{d_v, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        l_global lg_arg{d_l, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,   static_cast<unsigned int>(q_seq_len)};
-        o_global og_arg{d_o, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-
-        globals g{
-            qg_arg, 
-            kg_arg, 
-            vg_arg, 
-            lg_arg, 
-            og_arg, 
-            static_cast<int>(q_seq_len), 
-            static_cast<int>(hr), 
-            static_cast<int>(max_kv_blocks_per_q), 
-            reinterpret_cast<int32_t*>(q2k_block_sparse_index.data_ptr()), 
+    } else if (head_dim == 128) {
+        block_sparse_attention_forward_impl<128>(
+            d_q, d_k, d_v, d_l, d_o,
+            batch, qo_heads, kv_heads, seq_len, hr,
+            max_kv_blocks_per_q,
+            reinterpret_cast<int32_t*>(q2k_block_sparse_index.data_ptr()),
            reinterpret_cast<int32_t*>(q2k_block_sparse_num.data_ptr()),
-            reinterpret_cast<int32_t*>(kv_block_size.data_ptr())
-        };
-
-        constexpr int mem_size = 54000;
-
-        dim3 grid(q_seq_len/(BLOCK_M), qo_heads, batch);
-
-        cudaFuncSetAttribute(
-            fwd_attend_ker<128>,
-            cudaFuncAttributeMaxDynamicSharedMemorySize,
-            mem_size
+            reinterpret_cast<int32_t*>(block_size.data_ptr()),
+            stream
        );
-
-        fwd_attend_ker<128><<<grid, (128), mem_size, stream>>>(g);
-
-        CHECK_CUDA_ERROR(cudaGetLastError());
-        // cudaStreamSynchronize(stream);
+    } else {
+        TORCH_CHECK(false, "Unsupported head_dim: ", head_dim, ". Only 64 and 128 are supported.");
    }

    return {o, l_vec};
@@ -868,7 +921,7 @@ block_sparse_attention_backward(torch::Tensor q,
                   torch::Tensor og,
                   torch::Tensor k2q_block_sparse_index,
                   torch::Tensor k2q_block_sparse_num,
-                   torch::Tensor kv_block_size)
+                   torch::Tensor block_size)
 {
    CHECK_INPUT(q);
    CHECK_INPUT(k);
@@ -877,23 +930,11 @@ block_sparse_attention_backward(torch::Tensor q,
    CHECK_INPUT(o);
    CHECK_INPUT(og);

-    // q: [batch, qo_heads, q_seq_len, head_dim]
-    // k: [batch, kv_heads, kv_seq_len, head_dim]
-    // v: [batch, kv_heads, kv_seq_len, head_dim]
-    // o: [batch, qo_heads, q_seq_len, head_dim]
-    // l_vec: [batch, qo_heads, q_seq_len, 1]
-    // og: [batch, qo_heads, q_seq_len, head_dim]
-    // k2q_block_sparse_index: [batch, kv_heads, num_kv_blocks, max_num_q_blocks]
-    // k2q_block_sparse_num: [batch, kv_heads, num_kv_blocks]
-    // kv_block_size: [num_kv_blocks]
-
    auto batch    = q.size(0);
-    auto q_seq_len  = q.size(2);
-    auto kv_seq_len = k.size(2);
+    auto seq_len  = q.size(2);
    auto head_dim = q.size(3);
    auto max_q_blocks_per_kv = k2q_block_sparse_index.size(3);
-    auto num_kv_blocks = kv_block_size.size(0);
-    TORCH_CHECK(k2q_block_sparse_index.size(2) == num_kv_blocks, "k2q_block_sparse_index.size(2) must match num_kv_blocks (kv_block_size.size(0))");
+    TORCH_CHECK(k2q_block_sparse_index.size(2) == block_size.size(0), "k2q_block_sparse_index.size(2) must match block_size.size(0)");
    // check to see that these dimensions match for all inputs
    TORCH_CHECK(q.size(0)     == batch, "Q  batch dimension - idx 0 - must match for all inputs");
    TORCH_CHECK(k.size(0)     == batch, "K  batch dimension - idx 0 - must match for all inputs");
@@ -904,18 +945,23 @@ block_sparse_attention_backward(torch::Tensor q,
    TORCH_CHECK(k2q_block_sparse_index.size(0) == batch, "k2q_block_sparse_index batch dimension - idx 0 - must match for all inputs");
    TORCH_CHECK(k2q_block_sparse_num.size(0) == batch, "k2q_block_sparse_num batch dimension - idx 0 - must match for all inputs");

-    TORCH_CHECK(v.size(2)     == kv_seq_len, "V  sequence length dimension - idx 2 - must match K sequence length");
-    TORCH_CHECK(l_vec.size(2) == q_seq_len, "L  sequence length dimension - idx 2 - must match Q sequence length");
-    TORCH_CHECK(o.size(2)     == q_seq_len, "O  sequence length dimension - idx 2 - must match Q sequence length");
-    TORCH_CHECK(og.size(2)    == q_seq_len, "OG sequence length dimension - idx 2 - must match Q sequence length");
-    TORCH_CHECK(k2q_block_sparse_index.size(2) == num_kv_blocks, "k2q_block_sparse_index idx 2 - must match num_kv_blocks (kv_block_size.size(0))");
-    TORCH_CHECK(k2q_block_sparse_num.size(2) == num_kv_blocks, "k2q_block_sparse_num idx 2 - must match num_kv_blocks (kv_block_size.size(0))");
+
+    TORCH_CHECK(q.size(2)     == seq_len, "Q  sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(k.size(2)     == seq_len, "K  sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(v.size(2)     == seq_len, "V  sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(l_vec.size(2) == seq_len, "L  sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(o.size(2)     == seq_len, "O  sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(og.size(2)    == seq_len, "OG sequence length dimension - idx 2 - must match for all inputs");
+    TORCH_CHECK(k2q_block_sparse_index.size(2) == seq_len / BLOCK_N, "k2q_block_sparse_index idx 2 - must match seq_len / BLOCK_N");
+    TORCH_CHECK(k2q_block_sparse_num.size(2) == seq_len / BLOCK_N, "k2q_block_sparse_num idx 2 - must match seq_len / BLOCK_N");

    TORCH_CHECK(q.size(3)  == head_dim, "Q  head dimension - idx 3 - must match for all non-vector inputs");
    TORCH_CHECK(k.size(3)  == head_dim, "K  head dimension - idx 3 - must match for all non-vector inputs");
    TORCH_CHECK(v.size(3)  == head_dim, "V  head dimension - idx 3 - must match for all non-vector inputs");
    TORCH_CHECK(o.size(3)  == head_dim, "O  head dimension - idx 3 - must match for all non-vector inputs");
    TORCH_CHECK(og.size(3) == head_dim, "OG head dimension - idx 3 - must match for all non-vector inputs");
+    
+

    auto qo_heads = q.size(1);
    auto kv_heads = k.size(1);
@@ -942,20 +988,20 @@ block_sparse_attention_backward(torch::Tensor q,

    torch::Tensor qg = torch::zeros({static_cast<const uint>(batch), 
                                     static_cast<const uint>(qo_heads), 
-                                     static_cast<const uint>(q_seq_len), 
+                                     static_cast<const uint>(seq_len), 
                                     static_cast<const uint>(head_dim)},   l_vec.options());
    torch::Tensor kg = torch::zeros({static_cast<const uint>(batch), 
                                     static_cast<const uint>(kv_heads), 
-                                     static_cast<const uint>(kv_seq_len), 
+                                     static_cast<const uint>(seq_len), 
                                     static_cast<const uint>(head_dim)},   l_vec.options());
    torch::Tensor vg = torch::zeros({static_cast<const uint>(batch), 
                                     static_cast<const uint>(kv_heads), 
-                                     static_cast<const uint>(kv_seq_len), 
+                                     static_cast<const uint>(seq_len), 
                                     static_cast<const uint>(head_dim)},   l_vec.options());
    
    torch::Tensor d_vec = torch::empty({static_cast<const uint>(batch), 
                                        static_cast<const uint>(qo_heads), 
-                                        static_cast<const uint>(q_seq_len), 
+                                        static_cast<const uint>(seq_len), 
                                        static_cast<const uint>(1)},       l_vec.options());

    float*         qg_ptr = qg.data_ptr<float>();
@@ -984,7 +1030,7 @@ block_sparse_attention_backward(torch::Tensor q,
    //  cudaStreamSynchronize(stream);

    // TORCH_CHECK(seq_len % (4*kittens::TILE_DIM*4) == 0, "sequence length must be divisible by 256");
-    dim3 grid_bwd(q_seq_len/(PREP_NUM_WARPS*kittens::TILE_ROW_DIM<bf16>*4), qo_heads, batch);
+    dim3 grid_bwd(seq_len/(PREP_NUM_WARPS*kittens::TILE_ROW_DIM<bf16>*4), qo_heads, batch);

    if (head_dim == 64)  {
        using og_tile = st_bf<4*16, 64>;
@@ -997,9 +1043,9 @@ block_sparse_attention_backward(torch::Tensor q,

        using bwd_prep_globals = bwd_prep_globals<64>;

-        og_global prep_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        o_global  prep_o_arg {d_o,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        d_global  prep_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
+        og_global prep_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 64U};
+        o_global  prep_o_arg {d_o,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 64U};
+        d_global  prep_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};

        bwd_prep_globals bwd_g{prep_og_arg, prep_o_arg, prep_d_arg};

@@ -1036,15 +1082,15 @@ block_sparse_attention_backward(torch::Tensor q,

        using bwd_global_args = bwd_globals<64>;

-        bwd_q_global  bwd_q_arg {d_q,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        bwd_k_global  bwd_k_arg {d_k,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        bwd_v_global  bwd_v_arg {d_v,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        bwd_og_global bwd_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        bwd_qg_global bwd_qg_arg{d_qg, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 64U};
-        bwd_kg_global bwd_kg_arg{d_kg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        bwd_vg_global bwd_vg_arg{d_vg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 64U};
-        bwd_l_global  bwd_l_arg {d_l,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
-        bwd_d_global  bwd_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
+        bwd_q_global  bwd_q_arg {d_q,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_k_global  bwd_k_arg {d_k,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_v_global  bwd_v_arg {d_v,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_og_global bwd_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_qg_global bwd_qg_arg{d_qg, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_kg_global bwd_kg_arg{d_kg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_vg_global bwd_vg_arg{d_vg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 64U};
+        bwd_l_global  bwd_l_arg {d_l,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};
+        bwd_d_global  bwd_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};

        bwd_global_args bwd_global{bwd_q_arg, 
                        bwd_k_arg, 
@@ -1055,14 +1101,14 @@ block_sparse_attention_backward(torch::Tensor q,
                        bwd_vg_arg, 
                        bwd_l_arg, 
                        bwd_d_arg, 
-                        static_cast<int>(kv_seq_len), // N is not used in the kernel
+                        static_cast<int>(seq_len), 
                        static_cast<int>(hr),
                        static_cast<int>(max_q_blocks_per_kv),
                        reinterpret_cast<int32_t*>(k2q_block_sparse_index.data_ptr()),
                        reinterpret_cast<int32_t*>(k2q_block_sparse_num.data_ptr()),
-                        reinterpret_cast<int32_t*>(kv_block_size.data_ptr())};
+                        reinterpret_cast<int32_t*>(block_size.data_ptr())};

-        dim3 grid_bwd_2(kv_seq_len/BLOCK_N, qo_heads, batch);
+        dim3 grid_bwd_2(seq_len/64, qo_heads, batch);
        threads = 128;

        //cudadevicesynchronize();
@@ -1101,9 +1147,9 @@ block_sparse_attention_backward(torch::Tensor q,

        using bwd_prep_globals = bwd_prep_globals<128>;

-        og_global prep_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        o_global  prep_o_arg {d_o,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        d_global  prep_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
+        og_global prep_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 128U};
+        o_global  prep_o_arg {d_o,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 128U};
+        d_global  prep_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};

        bwd_prep_globals bwd_g{prep_og_arg, prep_o_arg, prep_d_arg};

@@ -1140,15 +1186,15 @@ block_sparse_attention_backward(torch::Tensor q,

        using bwd_global_args = bwd_globals<128>;

-        bwd_q_global  bwd_q_arg {d_q,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        bwd_k_global  bwd_k_arg {d_k,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        bwd_v_global  bwd_v_arg {d_v,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        bwd_og_global bwd_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        bwd_qg_global bwd_qg_arg{d_qg, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(q_seq_len), 128U};
-        bwd_kg_global bwd_kg_arg{d_kg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        bwd_vg_global bwd_vg_arg{d_vg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(kv_seq_len), 128U};
-        bwd_l_global  bwd_l_arg {d_l,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
-        bwd_d_global  bwd_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(q_seq_len)};
+        bwd_q_global  bwd_q_arg {d_q,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_k_global  bwd_k_arg {d_k,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_v_global  bwd_v_arg {d_v,  static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_og_global bwd_og_arg{d_og, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_qg_global bwd_qg_arg{d_qg, static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_kg_global bwd_kg_arg{d_kg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_vg_global bwd_vg_arg{d_vg, static_cast<unsigned int>(batch), static_cast<unsigned int>(kv_heads), static_cast<unsigned int>(seq_len), 128U};
+        bwd_l_global  bwd_l_arg {d_l,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};
+        bwd_d_global  bwd_d_arg {d_d,  static_cast<unsigned int>(batch), static_cast<unsigned int>(qo_heads), 1U,  static_cast<unsigned int>(seq_len)};

        bwd_global_args bwd_global{bwd_q_arg, 
                        bwd_k_arg, 
@@ -1159,14 +1205,14 @@ block_sparse_attention_backward(torch::Tensor q,
                        bwd_vg_arg, 
                        bwd_l_arg, 
                        bwd_d_arg, 
-                        static_cast<int>(kv_seq_len), // N is not used in the kernel
+                        static_cast<int>(seq_len), 
                        static_cast<int>(hr),
                        static_cast<int>(max_q_blocks_per_kv),
                        reinterpret_cast<int32_t*>(k2q_block_sparse_index.data_ptr()),
                        reinterpret_cast<int32_t*>(k2q_block_sparse_num.data_ptr()),
-                        reinterpret_cast<int32_t*>(kv_block_size.data_ptr())};
+                        reinterpret_cast<int32_t*>(block_size.data_ptr())};

-        dim3 grid_bwd_2(kv_seq_len/BLOCK_N, qo_heads, batch);
+        dim3 grid_bwd_2(seq_len/64, qo_heads, batch);
        threads = 128;

        //cudadevicesynchronize();
@@ -1187,4 +1233,4 @@ block_sparse_attention_backward(torch::Tensor q,

    return {qg, kg, vg};
    //cudadevicesynchronize();
-}
+}
@@ -4,7 +4,6 @@
 #include <torch/all.h>
 #include <torch/python.h>
 #include <cutlass/cutlass.h>
-#include <cutlass/numeric_types.h>
 #include "common/common.hpp"
 #include "norm/layernorm.hpp"

@@ -15,6 +14,10 @@ auto layer_norm(
  std::optional<at::Tensor const> const B,
  std::optional<at::Tensor> Output
 ) {
+  using ElementIn = float;
+  using ElementOut = float;
+  using ElementWeight = float;
+
  int64_t const m = Input.size(0);
  int64_t const n = Input.size(1);
  torch::Device const input_device = Input.device();
@@ -23,70 +26,31 @@ auto layer_norm(
    Output.emplace(
      torch::empty(
        {m, n},
-        torch::TensorOptions().device(input_device).dtype(Input.scalar_type())
+        torch::TensorOptions().device(input_device).dtype(torch::kFloat32)
      )
    );
  }

-  TORCH_CHECK(Output.value().scalar_type() == Input.scalar_type(),
-              "Output dtype must match Input dtype. Got Output=",
-              Output.value().scalar_type(), ", Input=", Input.scalar_type());
-  if (W.has_value()) {
-    TORCH_CHECK(W.value().scalar_type() == Input.scalar_type(),
-                "W dtype must match Input dtype. Got W=",
-                W.value().scalar_type(), ", Input=", Input.scalar_type());
-  }
-  if (B.has_value()) {
-    TORCH_CHECK(B.value().scalar_type() == Input.scalar_type(),
-                "B dtype must match Input dtype. Got B=",
-                B.value().scalar_type(), ", Input=", Input.scalar_type());
-  }

  void *Iptr = Input.data_ptr();
  void *Wptr = W.has_value() ? W.value().data_ptr() : nullptr;
  void *Bptr = B.has_value() ? B.value().data_ptr() : nullptr;
  void *Optr = Output.value().data_ptr();

-  auto stream = at::cuda::getCurrentCUDAStream().stream();
-  if (Input.scalar_type() == at::kHalf) {
-    using ElementIn = cutlass::half_t;
-    using ElementOut = cutlass::half_t;
-    using ElementWeight = cutlass::half_t;
-    BOOL_SWITCH(B.has_value(), BIAS, [&]{
-      BOOL_SWITCH(W.has_value(), AFFINE, [&]{
-        CONFIG_SWITCH(n, [&]{
-          layernorm<ElementIn, ElementOut, ElementWeight, AFFINE, BIAS, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-              Iptr, Wptr, Bptr, Optr, eps, m, n, stream);
-        });
+  BOOL_SWITCH(B.has_value(), BIAS, [&]{
+    BOOL_SWITCH(W.has_value(), AFFINE, [&]{
+    CONFIG_SWITCH(n, [&]{
+    layernorm<
+    ElementIn, ElementOut, ElementWeight,
+    AFFINE, BIAS,
+    MAX_HIDDEN_SIZE, NUM_THR_PER_CTA> (
+      Iptr, Wptr, Bptr,
+      Optr, eps, m, n,
+      at::cuda::getCurrentCUDAStream().stream()
+        );
      });
    });
-  } else if (Input.scalar_type() == at::kBFloat16) {
-    using ElementIn = cutlass::bfloat16_t;
-    using ElementOut = cutlass::bfloat16_t;
-    using ElementWeight = cutlass::bfloat16_t;
-    BOOL_SWITCH(B.has_value(), BIAS, [&]{
-      BOOL_SWITCH(W.has_value(), AFFINE, [&]{
-        CONFIG_SWITCH(n, [&]{
-          layernorm<ElementIn, ElementOut, ElementWeight, AFFINE, BIAS, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-              Iptr, Wptr, Bptr, Optr, eps, m, n, stream);
-        });
-      });
-    });
-  } else if (Input.scalar_type() == at::kFloat) {
-    using ElementIn = float;
-    using ElementOut = float;
-    using ElementWeight = float;
-    BOOL_SWITCH(B.has_value(), BIAS, [&]{
-      BOOL_SWITCH(W.has_value(), AFFINE, [&]{
-        CONFIG_SWITCH(n, [&]{
-          layernorm<ElementIn, ElementOut, ElementWeight, AFFINE, BIAS, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-              Iptr, Wptr, Bptr, Optr, eps, m, n, stream);
-        });
-      });
-    });
-  } else {
-    TORCH_CHECK(false, "Unsupported dtype for layer_norm_cuda: ", Input.scalar_type());
-  }
+  });
  
    

@@ -68,22 +68,9 @@ public:
    // mean reduction
    float u = _reduce_sum(x, shared_data) / params.n;

-    // IMPORTANT:
-    // Loader pads out-of-range lanes with 0. That is OK for the sum, but after
-    // subtracting mean, those padded lanes become -u and would incorrectly
-    // contribute to the variance. Mask them back to 0 before variance reduction.
-    // We launch exactly NumThrPerCta threads for a 1xMaxHiddenSize tile,
-    // so each thread is responsible for a contiguous chunk in N.
-    int thr_n_offset = tidx * NumElementPerThread;
    CUTLASS_PRAGMA_UNROLL
-    for (int i = 0; i < NumElementPerThread; ++i) {
-      int idx = thr_n_offset + i;
-      if (idx < params.n) {
-        x[i] -= u;
-      } else {
-        x[i] = 0.f;
-      }
-    }
+    for (int i = 0; i < NumElementPerThread; ++i)
+      x[i] -= u;

    __syncthreads();
    // var reduction
@@ -4,7 +4,6 @@
 #include <torch/all.h>
 #include <torch/python.h>
 #include <cutlass/cutlass.h>
-#include <cutlass/numeric_types.h>
 #include <pybind11/pybind11.h>

 #include "common/common.hpp"
@@ -17,6 +16,10 @@ auto rms_norm(
  std::optional<at::Tensor>& Output
 ) {
  
+  using ElementIn = float;
+  using ElementOut = float;
+  using ElementWeight = float;
+  
  int64_t const m = Input.size(0);
  int64_t const n = Input.size(1);
  torch::Device const input_device = Input.device();
@@ -25,51 +28,27 @@ auto rms_norm(
    Output.emplace(
      torch::empty(
        {m, n},
-        torch::TensorOptions().device(input_device).dtype(Input.scalar_type())
+        torch::TensorOptions().device(input_device).dtype(torch::kFloat32)
      )
    );
  }

-  TORCH_CHECK(Output.value().scalar_type() == Input.scalar_type(),
-              "Output dtype must match Input dtype. Got Output=",
-              Output.value().scalar_type(), ", Input=", Input.scalar_type());
-  if (Weight.has_value()) {
-    TORCH_CHECK(Weight.value().scalar_type() == Input.scalar_type(),
-                "Weight dtype must match Input dtype. Got Weight=",
-                Weight.value().scalar_type(), ", Input=", Input.scalar_type());
-  }
-
  void *Iptr = Input.data_ptr();
  void *Wptr = Weight.has_value() ? Weight.value().data_ptr() : nullptr;
  void *Optr = Output.value().data_ptr();

-  if (Input.scalar_type() == at::kHalf) {
-    using ElementIn = cutlass::half_t;
-    using ElementOut = cutlass::half_t;
-    using ElementWeight = cutlass::half_t;
-    CONFIG_SWITCH(n, [&]{
-      rmsnorm<ElementIn, ElementOut, ElementWeight, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-          Iptr, Wptr, Optr, eps, m, n, at::cuda::getCurrentCUDAStream().stream());
-    });
-  } else if (Input.scalar_type() == at::kBFloat16) {
-    using ElementIn = cutlass::bfloat16_t;
-    using ElementOut = cutlass::bfloat16_t;
-    using ElementWeight = cutlass::bfloat16_t;
-    CONFIG_SWITCH(n, [&]{
-      rmsnorm<ElementIn, ElementOut, ElementWeight, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-          Iptr, Wptr, Optr, eps, m, n, at::cuda::getCurrentCUDAStream().stream());
-    });
-  } else if (Input.scalar_type() == at::kFloat) {
-    using ElementIn = float;
-    using ElementOut = float;
-    using ElementWeight = float;
-    CONFIG_SWITCH(n, [&]{
-      rmsnorm<ElementIn, ElementOut, ElementWeight, MAX_HIDDEN_SIZE, NUM_THR_PER_CTA>(
-          Iptr, Wptr, Optr, eps, m, n, at::cuda::getCurrentCUDAStream().stream());
-    });
-  } else {
-    TORCH_CHECK(false, "Unsupported dtype for rms_norm_cuda: ", Input.scalar_type());
-  }
+
+  CONFIG_SWITCH(n, [&]{
+    rmsnorm<
+    ElementIn, ElementOut, ElementWeight,
+    MAX_HIDDEN_SIZE, NUM_THR_PER_CTA
+    > (
+      Iptr, Wptr,
+      Optr, 
+      eps, m, n, 
+      at::cuda::getCurrentCUDAStream().stream()
+    );
+});
  

  return Output;
@@ -9,7 +9,7 @@ build-backend = "scikit_build_core.build"

 [project]
 name = "fastvideo-kernel"
-version = "0.2.5"
+version = "0.2.1"
 description = "Unified CUDA kernels for FastVideo"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -1,295 +0,0 @@
-from __future__ import annotations
-
-import os
-from typing import Tuple
-
-import torch
-
-
-def _get_sm90_ops():
-    try:
-        from fastvideo_kernel._C import fastvideo_kernel_ops  # type: ignore
-    except Exception:
-        return None, None
-    return (
-        getattr(fastvideo_kernel_ops, "block_sparse_fwd", None),
-        getattr(fastvideo_kernel_ops, "block_sparse_bwd", None),
-    )
-
-
-def _is_sm90() -> bool:
-    if not torch.cuda.is_available():
-        return False
-    major, minor = torch.cuda.get_device_capability(0)
-    return major == 9 and minor == 0
-
-
-def _force_triton() -> bool:
-    # Force Triton even on SM90 and even if the compiled extension is available.
-    # Useful for CI / debugging / parity testing.
-    return os.environ.get("FASTVIDEO_KERNEL_VSA_FORCE_TRITON", "0") == "1"
-
-
-def _map_to_index(block_map: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
-    """
-    Preferred map->index conversion used by the wrapper.
-
-    This wrapper **requires** the Triton implementation.
-    If Triton (or the Triton map_to_index module) is not available, it raises.
-    """
-    if block_map.dim() == 3:
-        block_map = block_map.unsqueeze(0)
-    if block_map.dim() != 4:
-        raise ValueError(f"block_map must be [B,H,Q,KV] (or [H,Q,KV]), got shape={tuple(block_map.shape)}")
-    if block_map.dtype != torch.bool:
-        block_map = block_map.to(torch.bool)
-
-    if not block_map.is_cuda:
-        raise RuntimeError("block_map must be a CUDA tensor (Triton map_to_index required).")
-
-    try:
-        from fastvideo_kernel.triton_kernels.index import map_to_index as triton_map_to_index  # local import
-    except Exception as e:
-        raise ImportError(
-            "Triton map_to_index is required but not available. "
-            "Ensure Triton is installed and fastvideo_kernel.triton_kernels.index is importable."
-        ) from e
-    return triton_map_to_index(block_map)
-
-
-@torch.library.custom_op(
-    "fastvideo_kernel::block_sparse_attn_triton",
-    mutates_args=(),
-    device_types="cuda",
-)
-def block_sparse_attn_triton(
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    q = q.contiguous()
-    k = k.contiguous()
-    v = v.contiguous()
-    block_map = block_map.to(torch.bool)
-    q2k_idx, q2k_num = _map_to_index(block_map)
-
-    from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import (  # local import
-        triton_block_sparse_attn_forward,
-    )
-
-    o, M = triton_block_sparse_attn_forward(q, k, v, q2k_idx, q2k_num, variable_block_sizes)
-    return o, M
-
-
-
-@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_triton")
-def _block_sparse_attn_triton_fake(
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    o = torch.empty_like(q)
-    M = torch.empty((q.shape[0], q.shape[1], q.shape[2]), device=q.device, dtype=torch.float32)
-    return o, M
-
-
-@torch.library.custom_op(
-    "fastvideo_kernel::block_sparse_attn_backward_triton",
-    mutates_args=(),
-    device_types="cuda",
-)
-def block_sparse_attn_backward_triton(
-    grad_output: torch.Tensor,
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    o: torch.Tensor,
-    M: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    grad_output = grad_output.contiguous()
-    block_map = block_map.to(torch.bool)
-    q2k_idx, q2k_num = _map_to_index(block_map)
-    k2q_idx, k2q_num = _map_to_index(block_map.transpose(-1, -2).contiguous())
-
-    from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import (  # local import
-        triton_block_sparse_attn_backward,
-    )
-
-    dq, dk, dv = triton_block_sparse_attn_backward(
-        grad_output, q, k, v, o, M, q2k_idx, q2k_num, k2q_idx, k2q_num, variable_block_sizes
-    )
-    return dq, dk, dv
-
-
-@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_backward_triton")
-def _block_sparse_attn_backward_triton_fake(
-    grad_output: torch.Tensor,
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    o: torch.Tensor,
-    M: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    dq = torch.empty_like(q)
-    dk = torch.empty_like(k)
-    dv = torch.empty_like(v)
-    return dq, dk, dv
-
-
-def _backward_triton(ctx, grad_o, grad_M):
-    q, k, v, o, M, block_map, variable_block_sizes = ctx.saved_tensors
-    dq, dk, dv = block_sparse_attn_backward_triton(grad_o, q, k, v, o, M, block_map, variable_block_sizes)
-    return dq, dk, dv, None, None
-
-
-def _setup_context_triton(ctx, inputs, output):
-    q, k, v, block_map, variable_block_sizes = inputs
-    o, M = output
-    ctx.save_for_backward(q, k, v, o, M, block_map, variable_block_sizes)
-
-
-block_sparse_attn_triton.register_autograd(_backward_triton, setup_context=_setup_context_triton)
-
-
-@torch.library.custom_op(
-    "fastvideo_kernel::block_sparse_attn_sm90",
-    mutates_args=(),
-    device_types="cuda",
-)
-def block_sparse_attn_sm90(
-    q_padded: torch.Tensor,
-    k_padded: torch.Tensor,
-    v_padded: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    block_sparse_fwd, _ = _get_sm90_ops()
-    if block_sparse_fwd is None:
-        raise ImportError("fastvideo_kernel_ops.block_sparse_fwd is not available")
-
-    q_padded = q_padded.contiguous()
-    k_padded = k_padded.contiguous()
-    v_padded = v_padded.contiguous()
-    block_map = block_map.to(torch.bool)
-    q2k_idx, q2k_num = _map_to_index(block_map)
-
-    o_padded, lse_padded = block_sparse_fwd(
-        q_padded, k_padded, v_padded, q2k_idx, q2k_num, variable_block_sizes.int()
-    )
-    return o_padded, lse_padded
-
-
-@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_sm90")
-def _block_sparse_attn_sm90_fake(
-    q_padded: torch.Tensor,
-    k_padded: torch.Tensor,
-    v_padded: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    o = torch.empty_like(q_padded)
-    lse = torch.empty((q_padded.shape[0], q_padded.shape[1], q_padded.shape[2], 1), device=q_padded.device, dtype=torch.float32)
-    return o, lse
-
-
-@torch.library.custom_op(
-    "fastvideo_kernel::block_sparse_attn_backward_sm90",
-    mutates_args=(),
-    device_types="cuda",
-)
-def block_sparse_attn_backward_sm90(
-    grad_output_padded: torch.Tensor,
-    q_padded: torch.Tensor,
-    k_padded: torch.Tensor,
-    v_padded: torch.Tensor,
-    o_padded: torch.Tensor,
-    lse_padded: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    _, block_sparse_bwd = _get_sm90_ops()
-    if block_sparse_bwd is None:
-        raise ImportError("fastvideo_kernel_ops.block_sparse_bwd is not available")
-
-    grad_output_padded = grad_output_padded.contiguous()
-    block_map = block_map.to(torch.bool)
-    k2q_idx, k2q_num = _map_to_index(block_map.transpose(-1, -2).contiguous())
-
-    dq, dk, dv = block_sparse_bwd(
-        q_padded,
-        k_padded,
-        v_padded,
-        o_padded,
-        lse_padded,
-        grad_output_padded,
-        k2q_idx,
-        k2q_num,
-        variable_block_sizes.int(),
-    )
-    # C++ kernel returns fp32 grads; cast back to match PyTorch convention if needed
-    return dq.to(grad_output_padded.dtype), dk.to(grad_output_padded.dtype), dv.to(grad_output_padded.dtype)
-
-
-@torch.library.register_fake("fastvideo_kernel::block_sparse_attn_backward_sm90")
-def _block_sparse_attn_backward_sm90_fake(
-    grad_output_padded: torch.Tensor,
-    q_padded: torch.Tensor,
-    k_padded: torch.Tensor,
-    v_padded: torch.Tensor,
-    o_padded: torch.Tensor,
-    lse_padded: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    dq = torch.empty_like(q_padded)
-    dk = torch.empty_like(k_padded)
-    dv = torch.empty_like(v_padded)
-    return dq, dk, dv
-
-
-def _backward_sm90(ctx, grad_o, grad_lse):
-    q, k, v, o, lse, block_map, variable_block_sizes = ctx.saved_tensors
-    dq, dk, dv = block_sparse_attn_backward_sm90(
-        grad_o, q, k, v, o, lse, block_map, variable_block_sizes
-    )
-    return dq, dk, dv, None, None
-
-
-def _setup_context_sm90(ctx, inputs, output):
-    q, k, v, block_map, variable_block_sizes = inputs
-    o, lse = output
-    ctx.save_for_backward(q, k, v, o, lse, block_map, variable_block_sizes)
-
-
-block_sparse_attn_sm90.register_autograd(_backward_sm90, setup_context=_setup_context_sm90)
-
-
-def block_sparse_attn(
-    q: torch.Tensor,
-    k: torch.Tensor,
-    v: torch.Tensor,
-    block_map: torch.Tensor,
-    variable_block_sizes: torch.Tensor,
-) -> Tuple[torch.Tensor, torch.Tensor]:
-    """
-    Unified block-sparse attention op with autograd support.
-    - On SM90 with compiled extension present: uses fastvideo_kernel_ops.block_sparse_fwd/bwd.
-    - Otherwise: uses Triton implementation (requires q/k/v to have same padded length today).
-    """
-    block_sparse_fwd, block_sparse_bwd = _get_sm90_ops()
-    if (not _force_triton()) and _is_sm90() and (block_sparse_fwd is not None) and (block_sparse_bwd is not None):
-        return block_sparse_attn_sm90(q, k, v, block_map, variable_block_sizes)
-    # Triton path: generally assumes q/k/v share the same padded length
-    if q.shape[2] != k.shape[2] or q.shape[2] != v.shape[2]:
-        raise RuntimeError("Triton fallback requires q/k/v to have the same padded length.")
-    return block_sparse_attn_triton(q, k, v, block_map, variable_block_sizes)
-
-
@@ -1,6 +1,5 @@
 import math
 import torch
-from .block_sparse_attn import block_sparse_attn
 from .triton_kernels.block_sparse_attn_triton import triton_block_sparse_attn_forward
 from .triton_kernels.st_attn_triton import sliding_tile_attention_triton
 from .triton_kernels.index import map_to_index
@@ -46,22 +45,14 @@ def sliding_tile_attention(
    flag = shape_map[seq_shape]

    for head_idx, (t, h, w) in enumerate(window_size):
-        # Per-head slices are not contiguous in the batch dimension when batch>1
-        # (they keep the original head-stride). The TK kernel assumes contiguous
-        # [B, H, S, D] layout, so we materialize a contiguous [B,1,S,D] view.
-        q_h = q[:, head_idx:head_idx + 1].contiguous()
-        k_h = k[:, head_idx:head_idx + 1].contiguous()
-        v_h = v[:, head_idx:head_idx + 1].contiguous()
-        o_h = torch.empty_like(q_h)
        sta_fwd(
-            q_h, k_h,
-            v_h, o_h,
+            q[:, head_idx:head_idx + 1], k[:, head_idx:head_idx + 1],
+            v[:, head_idx:head_idx + 1], output[:, head_idx:head_idx + 1],
            t, h, w, text_length, False, has_text, flag
        )
-        output[:, head_idx:head_idx + 1] = o_h

    if has_text:
-        sta_fwd(q.contiguous(), k.contiguous(), v.contiguous(), output, 3, 3, 3, text_length, True, True, flag)
+        sta_fwd(q, k, v, output, 3, 3, 3, text_length, True, True, flag)

    return output[:, :, :seq_length]

@@ -71,7 +62,6 @@ def video_sparse_attn(
    k: torch.Tensor,
    v: torch.Tensor,
    variable_block_sizes: torch.Tensor,
-    q_variable_block_sizes: torch.Tensor,
    topk: int,
    block_size: int | tuple = 64,
    compress_attn_weight: torch.Tensor = None,
@@ -80,42 +70,14 @@ def video_sparse_attn(
        block_size = (block_size, block_size, block_size)

    block_elements = block_size[0] * block_size[1] * block_size[2]
-    batch, heads, q_seq_len, dim = q.shape
-    kv_seq_len = k.shape[2]
-    if v.shape[2] != kv_seq_len:
-        raise ValueError(
-            f"Expected k and v to have the same sequence length, got "
-            f"k.shape[2]={kv_seq_len}, v.shape[2]={v.shape[2]}"
-        )
-    if k.shape[0] != batch or v.shape[0] != batch or k.shape[1] != heads or v.shape[1] != heads:
-        raise ValueError("Expected q/k/v to have the same batch and head dimensions.")
-
-    if q_seq_len % block_elements != 0 or kv_seq_len % block_elements != 0:
-        raise ValueError(
-            f"q_seq_len and kv_seq_len must be divisible by block_elements={block_elements}, "
-            f"got q_seq_len={q_seq_len}, kv_seq_len={kv_seq_len}"
-        )
-    q_num_blocks = q_seq_len // block_elements
-    kv_num_blocks = kv_seq_len // block_elements
-
-    if variable_block_sizes.numel() != kv_num_blocks:
-        raise ValueError(
-            f"variable_block_sizes must have length kv_num_blocks={kv_num_blocks}, "
-            f"got {variable_block_sizes.numel()}"
-        )
-
-    if q_variable_block_sizes.numel() != q_num_blocks:
-        raise ValueError(
-            f"q_variable_block_sizes must have length q_num_blocks={q_num_blocks}, "
-            f"got {q_variable_block_sizes.numel()}"
-        )
+    batch, heads, seq_len, dim = q.shape

    # Compression branch
-    q_c = q.view(batch, heads, q_num_blocks, block_elements, dim)
-    k_c = k.view(batch, heads, kv_num_blocks, block_elements, dim)
-    v_c = v.view(batch, heads, kv_num_blocks, block_elements, dim)
+    q_c = q.view(batch, heads, seq_len // block_elements, block_elements, dim)
+    k_c = k.view(batch, heads, seq_len // block_elements, block_elements, dim)
+    v_c = v.view(batch, heads, seq_len // block_elements, block_elements, dim)

-    q_c = (q_c.float().sum(dim=3) / q_variable_block_sizes.view(1, 1, -1, 1)).to(
+    q_c = (q_c.float().sum(dim=3) / variable_block_sizes.view(1, 1, -1, 1)).to(
        q.dtype)
    k_c = (k_c.float().sum(dim=3) / variable_block_sizes.view(1, 1, -1, 1)).to(
        k.dtype)
@@ -126,9 +88,9 @@ def video_sparse_attn(
    attn = torch.softmax(scores, dim=-1)
    out_c = torch.matmul(attn, v_c)

-    out_c = out_c.view(batch, heads, q_num_blocks, 1, dim)
+    out_c = out_c.view(batch, heads, seq_len // block_elements, 1, dim)
    out_c = out_c.repeat(1, 1, 1, block_elements,
-                         1).view(batch, heads, q_seq_len, dim)
+                         1).view(batch, heads, seq_len, dim)

    # Sparse branch
    topk_idx = torch.topk(scores, topk, dim=-1).indices
@@ -138,17 +100,12 @@ def video_sparse_attn(
    idx, num = map_to_index(mask)
    
    if block_sparse_fwd is not None:
-        # Use autograd-enabled wrapper so backward works (and still uses SM90 kernel when available)
-        out_s = block_sparse_attn(q, k, v, mask, variable_block_sizes)[0]
+        out_s = block_sparse_fwd(
+            q, k, v, idx, num, variable_block_sizes.int()
+        )[0] # block_sparse_fwd returns vector<Tensor>
    else:
-        if q_seq_len != kv_seq_len:
-            raise RuntimeError(
-                "q/k have different lengths, but the compiled CUDA kernel (block_sparse_fwd) "
-                "is not available. The Triton fallback currently requires q and k/v to have "
-                "the same padded length."
-            )
-        # Triton-only forward (kept for environments without the wrapper deps)
-        out_s, _ = triton_block_sparse_attn_forward(q, k, v, idx, num, variable_block_sizes)
+        out_s, _ = triton_block_sparse_attn_forward(q, k, v, idx, num,
+                                                    variable_block_sizes)

    if compress_attn_weight is not None:
        return out_c * compress_attn_weight + out_s
@@ -1,311 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# Adapted from TurboDiffusion SLA implementation
-# Copyright (c) 2025 by SLA team.
-#
-# Citation:
-# @article{zhang2025sla,
-#   title={SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention},
-#   author={Jintao Zhang and Haoxu Wang and Kai Jiang and Shuo Yang and Kaiwen Zheng and
-#           Haocheng Xi and Ziteng Wang and Hongzhou Zhu and Min Zhao and Ion Stoica and
-#           Joseph E. Gonzalez and Jun Zhu and Jianfei Chen},
-#   journal={arXiv preprint arXiv:2509.24006},
-#   year={2025}
-# }
-
-import torch
-import triton
-import triton.language as tl
-
-
-@triton.jit
-def _attn_fwd(
-    Q, K, V,
-    qk_scale: tl.constexpr,
-    topk: tl.constexpr,
-    LUT, LSE, OS,
-    L: tl.constexpr,
-    M_BLOCKS: tl.constexpr,
-    D: tl.constexpr,
-    BLOCK_M: tl.constexpr,
-    BLOCK_N: tl.constexpr,
-):
-    idx_m = tl.program_id(0).to(tl.int64)
-    idx_bh = tl.program_id(1).to(tl.int64)
-
-    qkv_offset = idx_bh * L * D
-    lut_offset = (idx_bh * M_BLOCKS + idx_m) * topk
-    lse_offset = idx_bh * L
-    offs_m = idx_m * BLOCK_M + tl.arange(0, BLOCK_M)
-    offs_n = tl.arange(0, BLOCK_N)
-    offs_d = tl.arange(0, D)
-
-    Q_ptrs = Q + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    K_ptrs = K + qkv_offset + offs_n[None, :] * D + offs_d[:, None]
-    V_ptrs = V + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    OS_ptrs = OS + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    LUT_ptr = LUT + lut_offset
-    LSE_ptrs = LSE + lse_offset + offs_m
-    
-    m_i = tl.full([BLOCK_M], -float('inf'), dtype=tl.float32)
-    l_i = tl.zeros([BLOCK_M], dtype=tl.float32)
-    o_s = tl.zeros([BLOCK_M, D], dtype=tl.float32)
-
-    q = tl.load(Q_ptrs, mask=offs_m[:, None] < L)
-    for block_idx in tl.range(topk):
-        idx_n = tl.load(LUT_ptr + block_idx)
-        n_mask = offs_n < L - idx_n * BLOCK_N
-        
-        k = tl.load(K_ptrs + idx_n * BLOCK_N * D, mask=n_mask[None, :])
-        qk = tl.dot(q, k) * (qk_scale * 1.4426950408889634)  # = 1 / ln(2)
-        if L - idx_n * BLOCK_N < BLOCK_N:
-            qk = tl.where(n_mask[None, :], qk, float("-inf"))
-
-        v = tl.load(V_ptrs + idx_n * BLOCK_N * D, mask=n_mask[:, None])
-        local_m = tl.max(qk, 1)
-        new_m = tl.maximum(m_i, local_m)
-        qk = qk - new_m[:, None]
-
-        p = tl.math.exp2(qk)
-        l_ij = tl.sum(p, 1)
-        alpha = tl.math.exp2(m_i - new_m)
-        o_s = o_s * alpha[:, None]
-        o_s += tl.dot(p.to(v.dtype), v)
-
-        l_i = l_i * alpha + l_ij
-        m_i = new_m
-
-    o_s = o_s / l_i[:, None]
-    tl.store(OS_ptrs, o_s.to(OS.type.element_ty), mask=offs_m[:, None] < L)
-    
-    m_i += tl.math.log2(l_i)
-    tl.store(LSE_ptrs, m_i, mask=offs_m < L)
-
-
-@triton.jit
-def _attn_bwd_preprocess(
-    OS, DOS, DELTAS,
-    L,
-    D: tl.constexpr,
-    BLOCK_M: tl.constexpr,
-):
-    idx_m = tl.program_id(0).to(tl.int64)
-    idx_bh = tl.program_id(1).to(tl.int64)
-
-    OS += idx_bh * L * D
-    DOS += idx_bh * L * D
-    DELTAS += idx_bh * L
-
-    offs_m = idx_m * BLOCK_M + tl.arange(0, BLOCK_M)
-    offs_d = tl.arange(0, D)
-
-    o_s = tl.load(OS + offs_m[:, None] * D + offs_d[None, :], mask=offs_m[:, None] < L)
-    do_s = tl.load(DOS + offs_m[:, None] * D + offs_d[None, :], mask=offs_m[:, None] < L)
-    
-    delta_s = tl.sum(o_s * do_s, axis=1).to(DELTAS.type.element_ty)
-    tl.store(DELTAS + offs_m, delta_s, mask=offs_m < L)
-
-
-@triton.jit
-def _attn_bwd_dq(
-    Q, K, V, LSE, DELTAS,
-    DOS, DQ, LUT,
-    qk_scale: tl.constexpr,
-    topk: tl.constexpr,
-    L: tl.constexpr,
-    M_BLOCKS: tl.constexpr,
-    D: tl.constexpr,
-    BLOCK_M: tl.constexpr,
-    BLOCK_N: tl.constexpr,
-):
-    idx_m = tl.program_id(0).to(tl.int64)
-    idx_bh = tl.program_id(1).to(tl.int64)
-
-    offs_m = idx_m * BLOCK_M + tl.arange(0, BLOCK_M)
-    offs_n = tl.arange(0, BLOCK_N)
-    offs_d = tl.arange(0, D)
-
-    qkv_offset = idx_bh * L * D
-    lse_offset = idx_bh * L
-    lut_offset = (idx_bh * M_BLOCKS + idx_m) * topk
-
-    Q_ptrs = Q + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    K_ptrs = K + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    V_ptrs = V + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    DQ_ptrs = DQ + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    DOS_ptrs = DOS + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    LSE_ptrs = LSE + lse_offset + offs_m
-    DELTAS_ptrs = DELTAS + lse_offset + offs_m
-    LUT_ptr = LUT + lut_offset
-
-    q = tl.load(Q_ptrs, mask=offs_m[:, None] < L)
-    do_s = tl.load(DOS_ptrs, mask=offs_m[:, None] < L)
-    delta_s = tl.load(DELTAS_ptrs, mask=offs_m < L)
-    lse = tl.load(LSE_ptrs, mask=offs_m < L, other=float("inf"))
-    
-    dq = tl.zeros([BLOCK_M, D], dtype=tl.float32)
-    for block_idx in tl.range(topk, num_stages=2):
-        idx_n = tl.load(LUT_ptr + block_idx)
-        n_mask = offs_n < L - idx_n * BLOCK_N
-        
-        k = tl.load(K_ptrs + idx_n * BLOCK_N * D, mask=n_mask[:, None])
-        v = tl.load(V_ptrs + idx_n * BLOCK_N * D, mask=n_mask[:, None])
-        qk = tl.dot(q, k.T) * (qk_scale * 1.4426950408889634)
-        p = tl.math.exp2(qk - lse[:, None])
-        p = tl.where(n_mask[None, :], p, 0.0)
-        
-        dp = tl.dot(do_s, v.T).to(tl.float32)
-        ds = p * (dp - delta_s[:, None])
-        dq += tl.dot(ds.to(k.dtype), k)
-    tl.store(DQ_ptrs, dq * qk_scale, mask=offs_m[:, None] < L)
-    
-
-@triton.jit
-def _attn_bwd_dkdv(
-    Q, K, V, DOS, DK, DV,
-    qk_scale, KBID, LSE, DELTAS,
-    L: tl.constexpr,
-    M_BLOCKS: tl.constexpr,
-    N_BLOCKS: tl.constexpr,
-    D: tl.constexpr,
-    BLOCK_M: tl.constexpr,
-    BLOCK_N: tl.constexpr,
-    BLOCK_SLICE_FACTOR: tl.constexpr,
-):
-    BLOCK_M2: tl.constexpr = BLOCK_M // BLOCK_SLICE_FACTOR
-
-    idx_n = tl.program_id(0).to(tl.int64)
-    idx_bh = tl.program_id(1).to(tl.int64)
-
-    offs_n = idx_n * BLOCK_N + tl.arange(0, BLOCK_N)
-    offs_m = tl.arange(0, BLOCK_M2)
-    offs_d = tl.arange(0, D)
-
-    qkv_offset = idx_bh * L * D
-    kbid_offset = idx_bh * M_BLOCKS * N_BLOCKS
-    lse_offset = idx_bh * L
-
-    Q_ptrs = Q + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    K_ptrs = K + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    V_ptrs = V + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    DOS_ptrs = DOS + qkv_offset + offs_m[:, None] * D + offs_d[None, :]
-    DK_ptrs = DK + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    DV_ptrs = DV + qkv_offset + offs_n[:, None] * D + offs_d[None, :]
-    LSE_ptrs = LSE + lse_offset + offs_m
-    DELTAS_ptrs = DELTAS + lse_offset + offs_m
-    KBID_ptr = KBID + kbid_offset + idx_n
-
-    k = tl.load(K_ptrs, mask=offs_n[:, None] < L)
-    v = tl.load(V_ptrs, mask=offs_n[:, None] < L)
-        
-    dk = tl.zeros([BLOCK_N, D], dtype=tl.float32)
-    dv = tl.zeros([BLOCK_N, D], dtype=tl.float32)
-    for idx_m in tl.range(0, L, BLOCK_M2):
-        kbid = tl.load(KBID_ptr)
-        if kbid == 1:
-            m_mask = offs_m < L - idx_m
-            q = tl.load(Q_ptrs, mask=m_mask[:, None])
-            lse = tl.load(LSE_ptrs, mask=m_mask, other=float("inf"))
-            qkT = tl.dot(k, q.T) * (qk_scale * 1.4426950408889634)
-            pT = tl.math.exp2(qkT - lse[None, :])
-            pT = tl.where(offs_n[:, None] < L, pT, 0.0)
-
-            do = tl.load(DOS_ptrs, mask=m_mask[:, None])
-            dv += tl.dot(pT.to(do.dtype), do)
-            delta = tl.load(DELTAS_ptrs, mask=m_mask)
-            dpT = tl.dot(v, tl.trans(do))
-            dsT = pT * (dpT - delta[None, :])
-            dk += tl.dot(dsT.to(q.dtype), q)
-        
-        Q_ptrs += BLOCK_M2 * D
-        DOS_ptrs += BLOCK_M2 * D
-        LSE_ptrs += BLOCK_M2
-        DELTAS_ptrs += BLOCK_M2
-        if (idx_m + BLOCK_M2) % BLOCK_M == 0:
-            KBID_ptr += N_BLOCKS
-
-    tl.store(DK_ptrs, dk * qk_scale, mask=offs_n[:, None] < L)
-    tl.store(DV_ptrs, dv, mask=offs_n[:, None] < L)
-    
-
-class _attention(torch.autograd.Function):
-    """Sparse attention forward/backward with autograd support."""
-    
-    @staticmethod
-    def forward(ctx, q, k, v, k_block_id, lut, topk, BLOCK_M, BLOCK_N, qk_scale=None):
-        assert q.is_contiguous() and k.is_contiguous() and v.is_contiguous()
-        assert k_block_id.is_contiguous() and lut.is_contiguous()
-
-        assert BLOCK_M == 64 or BLOCK_M == 128
-        assert BLOCK_N == 64
-
-        B, H, L, D = q.shape
-        if qk_scale is None:
-            qk_scale = D**-0.5
-
-        M_BLOCKS = triton.cdiv(L, BLOCK_M)
-
-        o_s = torch.empty_like(v)
-        lse = torch.empty(q.shape[:-1], device=q.device, dtype=torch.float32)
-
-        grid = (M_BLOCKS, B * H)
-        _attn_fwd[grid](
-            q, k, v, qk_scale, topk,
-            lut, lse, o_s,
-            L, M_BLOCKS,
-            D, BLOCK_M, BLOCK_N,
-            num_warps=4 if q.shape[-1] == 64 else 8,
-            num_stages=3
-        )
-        
-        ctx.save_for_backward(q, k, v, k_block_id, lut, lse, o_s)
-        ctx.qk_scale = qk_scale
-        ctx.topk = topk
-        ctx.BLOCK_M = BLOCK_M
-        ctx.BLOCK_N = BLOCK_N
-        return o_s
-
-    @staticmethod
-    def backward(ctx, do_s):
-        q, k, v, k_block_id, lut, lse, o_s = ctx.saved_tensors
-        do_s = do_s.contiguous()
-
-        BLOCK_M, BLOCK_N = ctx.BLOCK_M, ctx.BLOCK_N
-        B, H, L, D = q.shape
-
-        M_BLOCKS = triton.cdiv(L, BLOCK_M)
-        N_BLOCKS = triton.cdiv(L, BLOCK_N)
-
-        dq = torch.empty_like(q)
-        dk = torch.empty_like(k)
-        dv = torch.empty_like(v)
-        delta_s = torch.empty_like(lse)
-
-        grid = (M_BLOCKS, B * H)
-        _attn_bwd_preprocess[grid](
-            o_s, do_s, delta_s,
-            L, D, BLOCK_M,
-        )
-
-        grid = (M_BLOCKS, B * H)
-        _attn_bwd_dq[grid](
-            q, k, v, lse, delta_s,
-            do_s, dq, lut,
-            ctx.qk_scale, ctx.topk,
-            L, M_BLOCKS,
-            D, BLOCK_M, BLOCK_N,
-            num_warps=4 if q.shape[-1] == 64 else 8,
-            num_stages=4 if q.shape[-1] == 64 else 5
-        )
-
-        grid = (N_BLOCKS, B * H)
-        _attn_bwd_dkdv[grid](
-            q, k, v, do_s, dk, dv,
-            ctx.qk_scale, k_block_id, lse, delta_s,
-            L, M_BLOCKS, N_BLOCKS,
-            D, BLOCK_M, BLOCK_N,
-            BLOCK_SLICE_FACTOR=BLOCK_M // 64,
-            num_warps=4 if q.shape[-1] == 64 else 8,
-            num_stages=4 if q.shape[-1] == 64 else 5
-        )
-
-        return dq, dk, dv, None, None, None, None, None, None
@@ -1 +1 @@
-__version__ = "0.2.5"
+__version__ = "0.2.1"
@@ -42,13 +42,37 @@ def block_sparse_kernel_test(Q, K, V, block_sparse_mask, variable_block_sizes, q
    q_padded = vsa_pad(Q, q_non_pad_index, q_num_blocks, BLOCK_M)
    k_padded = vsa_pad(K, kv_non_pad_index, kv_num_blocks, BLOCK_M)
    v_padded = vsa_pad(V, kv_non_pad_index, kv_num_blocks, BLOCK_M)
-    # Use autograd-enabled wrapper (internally dispatches to SM90 kernel or Triton)
-    from fastvideo_kernel.block_sparse_attn import block_sparse_attn
-    output_padded, _aux = block_sparse_attn(
-        q_padded, k_padded, v_padded, block_sparse_mask, variable_block_sizes
-    )
+    # Use raw kernel or triton
+    try:
+        from fastvideo_kernel._C import fastvideo_kernel_ops
+        raw_kernel = getattr(fastvideo_kernel_ops, "block_sparse_fwd", None)
+    except ImportError:
+        raw_kernel = None

-    output = output_padded[:, :, q_non_pad_index, :]
+    from fastvideo_kernel.triton_kernels.index import map_to_index
+
+    
+    # Convert mask to indices
+    # block_sparse_mask is [H, M, N] bool
+    # We need to map it to index.
+    # block_sparse_mask needs to be expanded/reshaped? 
+    # generate_block_sparse_mask_for_function returns [H, NumBlocksQ, NumBlocksKV]
+    
+    # Ops.py logic:
+    # mask = torch.zeros_like(scores, dtype=torch.bool).scatter_(-1, topk_idx, True)
+    # idx, num = map_to_index(mask)
+    
+    idx, num = map_to_index(block_sparse_mask.unsqueeze(0)) # Add batch dim [1, H, M, N]
+    
+    if raw_kernel:
+        out_s = raw_kernel(q_padded, k_padded, v_padded, idx, num, variable_block_sizes.int())
+        output = out_s[0]
+    else:
+        # Fallback to triton testing if C++ not available
+        from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import triton_block_sparse_attn_forward
+        output, _ = triton_block_sparse_attn_forward(q_padded, k_padded, v_padded, idx, num, variable_block_sizes)
+
+    output = output[:, :, q_non_pad_index, :]
    output.backward(dO)
    return output, Q.grad, K.grad, V.grad

@@ -240,6 +264,7 @@ def generate_error_graphs_qkdiff(h, d, error_mode='all'):

    print("-" * 150)

+@pytest.mark.skip()
 def test_video_sparse_attention_backward():
    if not torch.cuda.is_available():
        return
@@ -3,7 +3,6 @@ import sys
 from typing import Tuple

 import torch
-import pytest

 from .utils import (
    generate_block_sparse_mask_for_function,
@@ -58,14 +57,23 @@ def block_sparse_forward_test(
    k_padded = ref.vsa_pad(K, kv_non_pad_index, kv_num_blocks, BLOCK_M)
    v_padded = ref.vsa_pad(V, kv_non_pad_index, kv_num_blocks, BLOCK_M)

-    # Use autograd-enabled wrapper (internally dispatches SM90 C++ vs Triton)
-    from fastvideo_kernel.block_sparse_attn import block_sparse_attn
+    # Use raw kernel or triton
    try:
-        out_padded, _aux = block_sparse_attn(
-            q_padded, k_padded, v_padded, block_sparse_mask, variable_block_sizes
+        from fastvideo_kernel._C import fastvideo_kernel_ops
+        raw_kernel = getattr(fastvideo_kernel_ops, "block_sparse_fwd", None)
+    except ImportError:
+        raw_kernel = None
+        
+    from fastvideo_kernel.triton_kernels.index import map_to_index
+    idx, num = map_to_index(block_sparse_mask)
+    
+    if raw_kernel:
+        out_padded = raw_kernel(q_padded, k_padded, v_padded, idx, num, variable_block_sizes.int())[0]
+    else:
+        from fastvideo_kernel.triton_kernels.block_sparse_attn_triton import triton_block_sparse_attn_forward
+        out_padded, _ = triton_block_sparse_attn_forward(
+            q_padded, k_padded, v_padded, idx, num, variable_block_sizes
        )
-    except RuntimeError as e:
-        pytest.skip(str(e))

    # Remove padding on the query side
    out = out_padded[:, :, q_non_pad_index, :]
@@ -148,6 +156,11 @@ def run_forward_qk_diff(
 ) -> Tuple[float, float]:
    """
    Forward-only correctness test for the case S_q != S_kv.
+
+    NOTE:
+      - The Triton backend supports different Q/KV logical lengths via padding.
+      - The SM90 (H100) CUDA backend currently assumes the same number of blocks
+        for Q and KV, so we skip this test there.
    """
    assert torch.cuda.is_available(), "VSA kernels require CUDA"

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0

 import torch
-from sageattn3 import sageattn3_blackwell
+from fastvideo.attention.backends.sageattn.api import sageattn_blackwell

 from fastvideo.attention.backends.abstract import (AttentionBackend,
                                                   AttentionImpl,
@@ -67,6 +67,6 @@ class SageAttention3Impl(AttentionImpl):
        query = query.transpose(1, 2)
        key = key.transpose(1, 2)
        value = value.transpose(1, 2)
-        output = sageattn3_blackwell(query, key, value, is_causal=self.causal)
+        output = sageattn_blackwell(query, key, value, is_causal=self.causal)
        output = output.transpose(1, 2)
        return output
@@ -1,587 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SLA (Sparse-Linear Attention) backend for FastVideo
-# Adapted from TurboDiffusion SLA implementation
-#
-# Copyright (c) 2025 by SLA team.
-# Citation:
-# @article{zhang2025sla,
-#   title={SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention},
-#   author={Jintao Zhang and Haoxu Wang and Kai Jiang and Shuo Yang and Kaiwen Zheng and
-#           Haocheng Xi and Ziteng Wang and Hongzhou Zhu and Min Zhao and Ion Stoica and
-#           Joseph E. Gonzalez and Jun Zhu and Jianfei Chen},
-#   journal={arXiv preprint arXiv:2509.24006},
-#   year={2025}
-# }
-
-from dataclasses import dataclass
-from typing import Any
-from collections.abc import Callable
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import triton
-import triton.language as tl
-
-from fastvideo.attention.backends.abstract import (
-    AttentionBackend,
-    AttentionImpl,
-    AttentionMetadata,
-    AttentionMetadataBuilder,
-)
-from fastvideo_kernel.triton_kernels.sla_triton import _attention
-from fastvideo.logger import init_logger
-
-logger = init_logger(__name__)
-
-# ============================================================================
-# SLA Utility functions (moved from sla_kernels/utils.py)
-# ============================================================================
-
-
-@triton.jit
-def compress_kernel(
-    X,
-    XM,
-    L: tl.constexpr,
-    D: tl.constexpr,
-    BLOCK_L: tl.constexpr,
-):
-    idx_l = tl.program_id(0)
-    idx_bh = tl.program_id(1)
-
-    offs_l = idx_l * BLOCK_L + tl.arange(0, BLOCK_L)
-    offs_d = tl.arange(0, D)
-
-    x_offset = idx_bh * L * D
-    xm_offset = idx_bh * ((L + BLOCK_L - 1) // BLOCK_L) * D
-    x = tl.load(X + x_offset + offs_l[:, None] * D + offs_d[None, :],
-                mask=offs_l[:, None] < L)
-
-    nx = min(BLOCK_L, L - idx_l * BLOCK_L)
-    x_mean = tl.sum(x, axis=0, dtype=tl.float32) / nx
-    tl.store(XM + xm_offset + idx_l * D + offs_d,
-             x_mean.to(XM.dtype.element_ty))
-
-
-def mean_pool(x: torch.Tensor, BLK: int) -> torch.Tensor:
-    """Mean pool tensor along sequence dimension with block size BLK."""
-    assert x.is_contiguous()
-
-    B, H, L, D = x.shape
-    L_BLOCKS = (L + BLK - 1) // BLK
-    x_mean = torch.empty((B, H, L_BLOCKS, D), device=x.device, dtype=x.dtype)
-
-    grid = (L_BLOCKS, B * H)
-    compress_kernel[grid](x, x_mean, L, D, BLK)
-    return x_mean
-
-
-def get_block_map(
-    q: torch.Tensor,
-    k: torch.Tensor,
-    topk_ratio: float,
-    BLKQ: int = 64,
-    BLKK: int = 64,
-) -> tuple[torch.Tensor, torch.Tensor, int]:
-    """Compute sparse block map for attention based on QK similarity.
-    
-    Args:
-        q: Query tensor of shape (B, H, L, D)
-        k: Key tensor of shape (B, H, L, D)
-        topk_ratio: Ratio of key blocks to attend to (0-1)
-        BLKQ: Query block size
-        BLKK: Key block size
-        
-    Returns:
-        sparse_map: Binary mask of shape (B, H, num_q_blocks, num_k_blocks)
-        lut: Top-k indices of shape (B, H, num_q_blocks, topk)
-        topk: Number of key blocks selected
-    """
-    arg_k = k - torch.mean(
-        k, dim=-2, keepdim=True)  # smooth-k technique from SageAttention
-    pooled_qblocks = mean_pool(q, BLKQ)
-    pooled_kblocks = mean_pool(arg_k, BLKK)
-    pooled_score = pooled_qblocks @ pooled_kblocks.transpose(-1, -2)
-
-    K = pooled_score.shape[-1]
-    topk = min(K, int(topk_ratio * K))
-    lut = torch.topk(pooled_score, topk, dim=-1, sorted=False).indices
-
-    sparse_map = torch.zeros_like(pooled_score, dtype=torch.int8)
-    sparse_map.scatter_(-1, lut, 1)
-    return sparse_map, lut, topk
-
-
-# ============================================================================
-# SLA Backend classes
-# ============================================================================
-
-
-class SLAAttentionBackend(AttentionBackend):
-    """Sparse-Linear Attention backend."""
-
-    accept_output_buffer: bool = True
-
-    @staticmethod
-    def get_supported_head_sizes() -> list[int]:
-        return [64, 128]
-
-    @staticmethod
-    def get_name() -> str:
-        return "SLA_ATTN"
-
-    @staticmethod
-    def get_impl_cls() -> type["SLAAttentionImpl"]:
-        return SLAAttentionImpl
-
-    @staticmethod
-    def get_metadata_cls() -> type["SLAAttentionMetadata"]:
-        return SLAAttentionMetadata
-
-    @staticmethod
-    def get_builder_cls() -> type["SLAAttentionMetadataBuilder"]:
-        return SLAAttentionMetadataBuilder
-
-
-@dataclass
-class SLAAttentionMetadata(AttentionMetadata):
-    """Metadata for SLA attention."""
-    current_timestep: int
-    topk_ratio: float = 0.5  # Ratio of key blocks to attend to
-
-
-class SLAAttentionMetadataBuilder(AttentionMetadataBuilder):
-    """Builder for SLA attention metadata."""
-
-    def __init__(self) -> None:
-        pass
-
-    def prepare(self) -> None:
-        pass
-
-    def build(
-        self,
-        current_timestep: int,
-        topk_ratio: float = 0.5,
-        **kwargs: dict[str, Any],
-    ) -> SLAAttentionMetadata:
-        return SLAAttentionMetadata(
-            current_timestep=current_timestep,
-            topk_ratio=topk_ratio,
-        )
-
-
-class SLAAttentionImpl(AttentionImpl, nn.Module):
-    """SLA attention implementation with learnable linear projection.
-    
-    This implementation combines sparse attention with linear attention,
-    using a learnable projection to blend the outputs. The sparse attention
-    uses a block-sparse pattern determined by QK similarity.
-    
-    Args:
-        num_heads: Number of attention heads
-        head_size: Dimension of each head
-        topk_ratio: Ratio of key blocks to attend to (0-1), default 0.5
-        feature_map: Feature map for linear attention ('softmax', 'elu', 'relu')
-        BLKQ: Query block size for sparse attention
-        BLKK: Key block size for sparse attention
-        use_bf16: Whether to use bfloat16 for computation
-    """
-
-    def __init__(
-        self,
-        num_heads: int,
-        head_size: int,
-        causal: bool = False,
-        softmax_scale: float | None = None,
-        num_kv_heads: int | None = None,
-        prefix: str = "",
-        # SLA-specific parameters - matched to TurboDiffusion defaults
-        topk_ratio: float = 0.1,  # TurboDiffusion uses topk=0.1
-        feature_map: str = "softmax",
-        BLKQ: int = 128,  # TurboDiffusion uses BLKQ=128
-        BLKK: int = 64,  # TurboDiffusion uses BLKK=64
-        use_bf16: bool = True,
-        **extra_impl_args,
-    ) -> None:
-        nn.Module.__init__(self)
-
-        self.num_heads = num_heads
-        self.head_size = head_size
-        self.softmax_scale = softmax_scale if softmax_scale else head_size**-0.5
-        self.causal = causal
-        self.prefix = prefix
-
-        # SLA-specific config
-        self.topk_ratio = topk_ratio
-        self.BLKQ = BLKQ
-        self.BLKK = BLKK
-        self.dtype = torch.bfloat16 if use_bf16 else torch.float16
-
-        # Learnable linear projection for combining sparse + linear attention
-        self.proj_l = nn.Linear(head_size, head_size, dtype=torch.float32)
-
-        # Feature map for linear attention
-        # Type annotation for callables
-        self.feature_map_q: Callable[[torch.Tensor], torch.Tensor]
-        self.feature_map_k: Callable[[torch.Tensor], torch.Tensor]
-        if feature_map == "elu":
-            self.feature_map_q = lambda x: F.elu(x) + 1
-            self.feature_map_k = lambda x: F.elu(x) + 1
-        elif feature_map == "relu":
-            self.feature_map_q = F.relu
-            self.feature_map_k = F.relu
-        elif feature_map == "softmax":
-            self.feature_map_q = lambda x: F.softmax(x, dim=-1)
-            self.feature_map_k = lambda x: F.softmax(x, dim=-1)
-        else:
-            raise ValueError(f"Unknown feature map: {feature_map}")
-
-        self._init_weights()
-
-    def _init_weights(self) -> None:
-        """Initialize projection weights to zero for residual-like behavior."""
-        with torch.no_grad():
-            nn.init.zeros_(self.proj_l.weight)
-            nn.init.zeros_(self.proj_l.bias)  # type: ignore[arg-type]
-
-    def _calc_linear_attention(
-        self,
-        q: torch.Tensor,
-        k: torch.Tensor,
-        v: torch.Tensor,
-    ) -> torch.Tensor:
-        """Compute linear attention: (Q @ K^T @ V) / normalizer.
-        
-        Args:
-            q: Query tensor (B, H, L, D) after feature map
-            k: Key tensor (B, H, L, D) after feature map
-            v: Value tensor (B, H, L, D)
-            
-        Returns:
-            Linear attention output (B, H, L, D)
-        """
-        kvsum = k.transpose(-1, -2) @ v  # (B, H, D, D)
-        ksum = torch.sum(k, dim=-2, keepdim=True)  # (B, H, 1, D)
-        return (q @ kvsum) / (1e-5 + (q * ksum).sum(dim=-1, keepdim=True))
-
-    def forward(
-        self,
-        query: torch.Tensor,
-        key: torch.Tensor,
-        value: torch.Tensor,
-        attn_metadata: AttentionMetadata,
-    ) -> torch.Tensor:
-        """Forward pass for SLA attention.
-        
-        Input tensors are in FastVideo format: (B, L, H, D)
-        Internally converted to SLA format: (B, H, L, D)
-        
-        Args:
-            query: Query tensor (B, L, H, D)
-            key: Key tensor (B, L, H, D)
-            value: Value tensor (B, L, H, D)
-            attn_metadata: Attention metadata
-            
-        Returns:
-            Output tensor (B, L, H, D)
-        """
-        original_dtype = query.dtype
-
-        # Convert from FastVideo format (B, L, H, D) to SLA format (B, H, L, D)
-        q = query.transpose(1, 2).contiguous()
-        k = key.transpose(1, 2).contiguous()
-        v = value.transpose(1, 2).contiguous()
-
-        # Get topk ratio from metadata if available
-        topk_ratio = self.topk_ratio
-        if hasattr(attn_metadata, 'topk_ratio'):
-            topk_ratio = attn_metadata.topk_ratio  # type: ignore[union-attr]
-
-        # Compute block-sparse attention pattern
-        sparse_map, lut, real_topk = get_block_map(q,
-                                                   k,
-                                                   topk_ratio=topk_ratio,
-                                                   BLKQ=self.BLKQ,
-                                                   BLKK=self.BLKK)
-
-        # Convert to compute dtype
-        q = q.to(self.dtype)
-        k = k.to(self.dtype)
-        v = v.to(self.dtype)
-
-        # Sparse attention
-        o_s = _attention.apply(q, k, v, sparse_map, lut, real_topk, self.BLKQ,
-                               self.BLKK)
-
-        # Linear attention with feature maps
-        q_linear = self.feature_map_q(q).contiguous().to(self.dtype)
-        k_linear = self.feature_map_k(k).contiguous().to(self.dtype)
-        o_l = self._calc_linear_attention(q_linear, k_linear, v)
-
-        # Project linear attention output and combine
-        with torch.amp.autocast('cuda', dtype=self.dtype):
-            o_l = self.proj_l(o_l)
-
-        # Combine sparse and linear outputs
-        output = (o_s + o_l).to(original_dtype)
-
-        # Convert back to FastVideo format (B, L, H, D)
-        output = output.transpose(1, 2)
-
-        return output
-
-
-# Check if spas_sage_attn is available for SageSLA
-SAGESLA_ENABLED = True
-try:
-    import spas_sage_attn._qattn as qattn
-    import spas_sage_attn._fused as fused
-    from spas_sage_attn.utils import get_vanilla_qk_quant, block_map_lut_triton
-except ImportError:
-    SAGESLA_ENABLED = False
-
-SAGE2PP_ENABLED = True
-try:
-    from spas_sage_attn._qattn import qk_int8_sv_f8_accum_f16_block_sparse_attn_inst_buf_fuse_v_scale_with_pv_threshold
-except ImportError:
-    SAGE2PP_ENABLED = False
-
-
-class SageSLAAttentionBackend(AttentionBackend):
-    """Quantized Sparse-Linear Attention backend using SageAttention kernels."""
-
-    accept_output_buffer: bool = True
-
-    @staticmethod
-    def get_supported_head_sizes() -> list[int]:
-        return [64, 128]
-
-    @staticmethod
-    def get_name() -> str:
-        return "SAGE_SLA_ATTN"
-
-    @staticmethod
-    def get_impl_cls() -> type["SageSLAAttentionImpl"]:
-        return SageSLAAttentionImpl
-
-    @staticmethod
-    def get_metadata_cls() -> type["SLAAttentionMetadata"]:
-        return SLAAttentionMetadata
-
-    @staticmethod
-    def get_builder_cls() -> type["SLAAttentionMetadataBuilder"]:
-        return SLAAttentionMetadataBuilder
-
-
-def _get_cuda_arch(device_index: int) -> str:
-    """Get CUDA architecture string for the given device."""
-    major, minor = torch.cuda.get_device_capability(device_index)
-    return f"sm{major}{minor}"
-
-
-class SageSLAAttentionImpl(AttentionImpl, nn.Module):
-    """SageSLA attention implementation using quantized SageAttention kernels.
-    
-    This uses INT8 quantization for Q/K and FP8 for V to achieve better performance
-    while maintaining accuracy. Requires spas_sage_attn package.
-    
-    Args:
-        num_heads: Number of attention heads
-        head_size: Dimension of each head (must be 64 or 128)
-        topk_ratio: Ratio of key blocks to attend to (0-1), default 0.5
-        feature_map: Feature map for linear attention ('softmax', 'elu', 'relu')
-        use_bf16: Whether to use bfloat16 for computation
-    """
-
-    def __init__(
-        self,
-        num_heads: int,
-        head_size: int,
-        causal: bool = False,
-        softmax_scale: float | None = None,
-        num_kv_heads: int | None = None,
-        prefix: str = "",
-        # SageSLA-specific parameters
-        topk_ratio: float = 0.5,
-        feature_map: str = "softmax",
-        use_bf16: bool = True,
-        **extra_impl_args,
-    ) -> None:
-        nn.Module.__init__(self)
-
-        if not SAGESLA_ENABLED:
-            raise ImportError(
-                "SageSLA requires spas_sage_attn. "
-                "Install with: pip install git+https://github.com/thu-ml/SpargeAttn.git"
-            )
-
-        assert head_size in [
-            64, 128
-        ], f"SageSLA requires head_size in [64, 128], got {head_size}"
-
-        self.num_heads = num_heads
-        self.head_size = head_size
-        self.softmax_scale = softmax_scale if softmax_scale else head_size**-0.5
-        self.causal = causal
-        self.prefix = prefix
-
-        # SageSLA-specific config
-        self.topk_ratio = topk_ratio
-        self.dtype = torch.bfloat16 if use_bf16 else torch.float16
-
-        # Learnable linear projection for combining sparse + linear attention
-        self.proj_l = nn.Linear(head_size, head_size, dtype=torch.float32)
-
-        # Feature map for linear attention
-        # Type annotation for callables
-        self.feature_map_q: Callable[[torch.Tensor], torch.Tensor]
-        self.feature_map_k: Callable[[torch.Tensor], torch.Tensor]
-        if feature_map == "elu":
-            self.feature_map_q = lambda x: F.elu(x) + 1
-            self.feature_map_k = lambda x: F.elu(x) + 1
-        elif feature_map == "relu":
-            self.feature_map_q = F.relu
-            self.feature_map_k = F.relu
-        elif feature_map == "softmax":
-            self.feature_map_q = lambda x: F.softmax(x, dim=-1)
-            self.feature_map_k = lambda x: F.softmax(x, dim=-1)
-        else:
-            raise ValueError(f"Unknown feature map: {feature_map}")
-
-        self._init_weights()
-
-    def _init_weights(self) -> None:
-        """Initialize projection weights to zero for residual-like behavior."""
-        with torch.no_grad():
-            nn.init.zeros_(self.proj_l.weight)
-            nn.init.zeros_(self.proj_l.bias)  # type: ignore[arg-type]
-
-    def _calc_linear_attention(
-        self,
-        q: torch.Tensor,
-        k: torch.Tensor,
-        v: torch.Tensor,
-    ) -> torch.Tensor:
-        """Compute linear attention: (Q @ K^T @ V) / normalizer."""
-        kvsum = k.transpose(-1, -2) @ v
-        ksum = torch.sum(k, dim=-2, keepdim=True)
-        return (q @ kvsum) / (1e-5 + (q * ksum).sum(dim=-1, keepdim=True))
-
-    def forward(
-        self,
-        query: torch.Tensor,
-        key: torch.Tensor,
-        value: torch.Tensor,
-        attn_metadata: AttentionMetadata,
-    ) -> torch.Tensor:
-        """Forward pass for SageSLA attention with quantized kernels.
-        
-        Input tensors are in FastVideo format: (B, L, H, D)
-        
-        Args:
-            query: Query tensor (B, L, H, D)
-            key: Key tensor (B, L, H, D)
-            value: Value tensor (B, L, H, D)
-            attn_metadata: Attention metadata
-            
-        Returns:
-            Output tensor (B, L, H, D)
-        """
-        original_dtype = query.dtype
-
-        # Convert from FastVideo format (B, L, H, D) to SLA format (B, H, L, D)
-        q = query.transpose(1, 2).contiguous()
-        k = key.transpose(1, 2).contiguous()
-        v = value.transpose(1, 2).contiguous()
-
-        # Get topk ratio from metadata if available
-        topk_ratio = self.topk_ratio
-        if hasattr(attn_metadata, 'topk_ratio'):
-            topk_ratio = attn_metadata.topk_ratio  # type: ignore[union-attr]
-
-        # Determine block sizes based on GPU architecture
-        arch = _get_cuda_arch(q.device.index)
-        if arch == "sm90":
-            BLKQ, BLKK = 64, 128
-        else:
-            BLKQ, BLKK = 128, 64
-
-        # Compute block-sparse attention pattern
-        sparse_map, lut, real_topk = get_block_map(q,
-                                                   k,
-                                                   topk_ratio=topk_ratio,
-                                                   BLKQ=BLKQ,
-                                                   BLKK=BLKK)
-
-        # Convert to compute dtype
-        q = q.to(self.dtype)
-        k = k.to(self.dtype)
-        v = v.to(self.dtype)
-
-        # ========== SPARGE QUANTIZED ATTENTION ==========
-        km = k.mean(dim=-2, keepdim=True)
-        headdim = q.size(-1)
-        scale = 1.0 / (headdim**0.5)
-
-        # Quantize Q, K to INT8
-        q_int8, q_scale, k_int8, k_scale = get_vanilla_qk_quant(
-            q, k, km, BLKQ, BLKK)
-        lut_triton, valid_block_num = block_map_lut_triton(sparse_map)
-
-        # Quantize V to FP8
-        b, h_kv, kv_len, head_dim = v.shape
-        padded_len = (kv_len + 127) // 128 * 128
-        v_transposed_permutted = torch.empty((b, h_kv, head_dim, padded_len),
-                                             dtype=v.dtype,
-                                             device=v.device)
-        fused.transpose_pad_permute_cuda(v, v_transposed_permutted, 1)
-        v_fp8 = torch.empty(v_transposed_permutted.shape,
-                            dtype=torch.float8_e4m3fn,
-                            device=v.device)
-        v_scale = torch.empty((b, h_kv, head_dim),
-                              dtype=torch.float32,
-                              device=v.device)
-        fused.scale_fuse_quant_cuda(v_transposed_permutted, v_fp8, v_scale,
-                                    kv_len, 2.25, 1)
-
-        # Sparse attention with quantized kernels
-        o_s = torch.empty_like(q)
-        if arch == "sm90":
-            qattn.qk_int8_sv_f8_accum_f32_block_sparse_attn_inst_buf_fuse_v_scale_sm90(
-                q_int8, k_int8, v_fp8, o_s, lut_triton, valid_block_num,
-                q_scale, k_scale, v_scale, 1, False, 1, scale)
-        else:
-            pvthreshold = torch.full((q.shape[-3], ),
-                                     1e6,
-                                     dtype=torch.float32,
-                                     device=q.device)
-            if SAGE2PP_ENABLED:
-                qk_int8_sv_f8_accum_f16_block_sparse_attn_inst_buf_fuse_v_scale_with_pv_threshold(
-                    q_int8, k_int8, v_fp8, o_s, lut_triton, valid_block_num,
-                    pvthreshold, q_scale, k_scale, v_scale, 1, False, 1, scale,
-                    0)
-            else:
-                qattn.qk_int8_sv_f8_accum_f32_block_sparse_attn_inst_buf_fuse_v_scale_with_pv_threshold(
-                    q_int8, k_int8, v_fp8, o_s, lut_triton, valid_block_num,
-                    pvthreshold, q_scale, k_scale, v_scale, 1, False, 1, scale,
-                    0)
-        # ========== END SPARGE ==========
-
-        # Linear attention with feature maps
-        q_linear = self.feature_map_q(q).contiguous().to(self.dtype)
-        k_linear = self.feature_map_k(k).contiguous().to(self.dtype)
-        o_l = self._calc_linear_attention(q_linear, k_linear, v)
-
-        # Project linear attention output and combine
-        with torch.amp.autocast('cuda', dtype=self.dtype):
-            o_l = self.proj_l(o_l)
-
-        # Combine sparse and linear outputs
-        output = (o_s + o_l).to(original_dtype)
-
-        # Convert back to FastVideo format (B, L, H, D)
-        output = output.transpose(1, 2)
-
-        return output
@@ -276,9 +276,8 @@ class VideoSparseAttentionImpl(AttentionImpl):
            query,
            key,
            value,
-            attn_metadata.variable_block_sizes,
-            attn_metadata.variable_block_sizes,
-            cur_topk,
+            variable_block_sizes=attn_metadata.variable_block_sizes,
+            topk=cur_topk,
            block_size=VSA_TILE_SIZE,
            compress_attn_weight=gate_compress).transpose(1, 2)

@@ -50,10 +50,6 @@ class DistributedAttention(nn.Module):
                                  num_kv_heads=num_kv_heads,
                                  prefix=f"{prefix}.impl",
                                  **extra_impl_args)
-        # Register attn_impl as submodule if it has learnable parameters (e.g., SLA's proj_l)
-        # This ensures its parameters are included in state_dict() for saving/loading
-        if isinstance(self.attn_impl, nn.Module):
-            self.add_module('attn_impl', self.attn_impl)
        self.num_heads = num_heads
        self.head_size = head_size
        self.num_kv_heads = num_kv_heads
@@ -2,18 +2,5 @@ from fastvideo.configs.models.base import ModelConfig
 from fastvideo.configs.models.dits.base import DiTConfig
 from fastvideo.configs.models.encoders.base import EncoderConfig
 from fastvideo.configs.models.vaes.base import VAEConfig
-from fastvideo.configs.models.audio import (LTX2AudioDecoderConfig,
-                                            LTX2AudioEncoderConfig,
-                                            LTX2VocoderConfig)
-from fastvideo.configs.models.upsamplers.base import UpsamplerConfig

-__all__ = [
-    "ModelConfig",
-    "VAEConfig",
-    "DiTConfig",
-    "EncoderConfig",
-    "LTX2AudioEncoderConfig",
-    "LTX2AudioDecoderConfig",
-    "LTX2VocoderConfig",
-    "UpsamplerConfig",
-]
+__all__ = ["ModelConfig", "VAEConfig", "DiTConfig", "EncoderConfig"]
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-
-from fastvideo.configs.models.audio.ltx2_audio_vae import (
-    LTX2AudioDecoderConfig,
-    LTX2AudioEncoderConfig,
-    LTX2VocoderConfig,
-)
-
-__all__ = [
-    "LTX2AudioEncoderConfig",
-    "LTX2AudioDecoderConfig",
-    "LTX2VocoderConfig",
-]
@@ -1,31 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""
-LTX-2 audio VAE and vocoder configuration.
-"""
-
-from dataclasses import dataclass, field
-
-from fastvideo.configs.models.base import ArchConfig, ModelConfig
-
-
-@dataclass
-class LTX2AudioArchConfig(ArchConfig):
-    architectures: list[str] = field(default_factory=list)
-
-
-@dataclass
-class LTX2AudioEncoderConfig(ModelConfig):
-    arch_config: ArchConfig = field(default_factory=lambda: LTX2AudioArchConfig(
-        architectures=["LTX2AudioEncoder"]))
-
-
-@dataclass
-class LTX2AudioDecoderConfig(ModelConfig):
-    arch_config: ArchConfig = field(default_factory=lambda: LTX2AudioArchConfig(
-        architectures=["LTX2AudioDecoder"]))
-
-
-@dataclass
-class LTX2VocoderConfig(ModelConfig):
-    arch_config: ArchConfig = field(default_factory=lambda: LTX2AudioArchConfig(
-        architectures=["LTX2Vocoder"]))
@@ -3,13 +3,11 @@ from fastvideo.configs.models.dits.cosmos2_5 import Cosmos25VideoConfig
 from fastvideo.configs.models.dits.hunyuanvideo import HunyuanVideoConfig
 from fastvideo.configs.models.dits.hunyuanvideo15 import HunyuanVideo15Config
 from fastvideo.configs.models.dits.longcat import LongCatVideoConfig
-from fastvideo.configs.models.dits.ltx2 import LTX2VideoConfig
 from fastvideo.configs.models.dits.stepvideo import StepVideoConfig
 from fastvideo.configs.models.dits.wanvideo import WanVideoConfig
-from fastvideo.configs.models.dits.hyworld import HYWorldConfig

 __all__ = [
    "HunyuanVideoConfig", "HunyuanVideo15Config", "WanVideoConfig",
    "StepVideoConfig", "CosmosVideoConfig", "Cosmos25VideoConfig",
-    "LongCatVideoConfig", "LTX2VideoConfig", "HYWorldConfig"
+    "LongCatVideoConfig"
 ]
@@ -18,8 +18,7 @@ class DiTArchConfig(ArchConfig):
        AttentionBackendEnum.SLIDING_TILE_ATTN, AttentionBackendEnum.SAGE_ATTN,
        AttentionBackendEnum.FLASH_ATTN, AttentionBackendEnum.TORCH_SDPA,
        AttentionBackendEnum.VIDEO_SPARSE_ATTN, AttentionBackendEnum.VMOBA_ATTN,
-        AttentionBackendEnum.SAGE_ATTN_THREE, AttentionBackendEnum.SLA_ATTN,
-        AttentionBackendEnum.SAGE_SLA_ATTN)
+        AttentionBackendEnum.SAGE_ATTN_THREE)

    hidden_size: int = 0
    num_attention_heads: int = 0
@@ -55,8 +55,6 @@ class HunyuanVideo15ArchConfig(DiTArchConfig):
            r"txt_in.refiner_blocks.\1.mlp.fc_out.\2",
            r"^context_embedder\.token_refiner\.refiner_blocks\.(\d+)\.norm_out\.linear\.(.*)$":
            r"txt_in.refiner_blocks.\1.adaLN_modulation.linear.\2",
-            r"^context_embedder\.token_refiner\.refiner_blocks\.(\d+)\.self_attn_qkv\.(.*)$":
-            r"txt_in.refiner_blocks.\1.self_attn_qkv.\2",

            # 2. txt_in_2 mapping:
            r"^context_embedder_2\.(.*)$":
@@ -1,202 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-from dataclasses import dataclass, field
-
-from fastvideo.configs.models.dits.base import DiTArchConfig, DiTConfig
-
-
-def is_double_block(n: str, m) -> bool:
-    return "double" in n and str.isdigit(n.split(".")[-1])
-
-
-def is_refiner_block(n: str, m) -> bool:
-    return "refiner" in n and str.isdigit(n.split(".")[-1])
-
-
-def is_txt_in(n: str, m) -> bool:
-    return n.split(".")[-1] == "txt_in"
-
-
-@dataclass
-class HYWorldArchConfig(DiTArchConfig):
-    _fsdp_shard_conditions: list = field(
-        default_factory=lambda: [is_double_block, is_refiner_block])
-
-    _compile_conditions: list = field(
-        default_factory=lambda: [is_double_block, is_refiner_block, is_txt_in])
-
-    param_names_mapping: dict = field(
-        default_factory=lambda: {
-            # 1. txt_in submodules (text embedder, refiner blocks):
-            r"^txt_in\.t_embedder\.mlp\.0\.(.*)$":
-            r"txt_in.t_embedder.mlp.fc_in.\1",
-            r"^txt_in\.t_embedder\.mlp\.2\.(.*)$":
-            r"txt_in.t_embedder.mlp.fc_out.\1",
-            r"^txt_in\.c_embedder\.linear_1\.(.*)$":
-            r"txt_in.c_embedder.fc_in.\1",
-            r"^txt_in\.c_embedder\.linear_2\.(.*)$":
-            r"txt_in.c_embedder.fc_out.\1",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.norm1\.(.*)$":
-            r"txt_in.refiner_blocks.\1.norm1.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.norm2\.(.*)$":
-            r"txt_in.refiner_blocks.\1.norm2.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.self_attn_qkv\.(.*)$":
-            r"txt_in.refiner_blocks.\1.self_attn_qkv.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.self_attn_proj\.(.*)$":
-            r"txt_in.refiner_blocks.\1.self_attn_proj.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.mlp\.fc1\.(.*)$":
-            r"txt_in.refiner_blocks.\1.mlp.fc_in.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.mlp\.fc2\.(.*)$":
-            r"txt_in.refiner_blocks.\1.mlp.fc_out.\2",
-            r"^txt_in\.individual_token_refiner\.blocks\.(\d+)\.adaLN_modulation\.1\.(.*)$":
-            r"txt_in.refiner_blocks.\1.adaLN_modulation.linear.\2",
-
-            # 2. time_in mappings:
-            r"^time_in\.mlp\.0\.(.*)$":
-            r"time_in.timestep_embedder.mlp.fc_in.\1",
-            r"^time_in\.mlp\.2\.(.*)$":
-            r"time_in.timestep_embedder.mlp.fc_out.\1",
-
-            # 3. action_in mappings:
-            r"^action_in\.mlp\.0\.(.*)$":
-            r"action_in.mlp.fc_in.\1",
-            r"^action_in\.mlp\.2\.(.*)$":
-            r"action_in.mlp.fc_out.\1",
-
-            # 4. byt5_in -> txt_in_2 mappings:
-            r"^byt5_in\.layernorm\.(.*)$":
-            r"txt_in_2.norm.\1",
-            r"^byt5_in\.fc1\.(.*)$":
-            r"txt_in_2.linear_1.\1",
-            r"^byt5_in\.fc2\.(.*)$":
-            r"txt_in_2.linear_2.\1",
-            r"^byt5_in\.fc3\.(.*)$":
-            r"txt_in_2.linear_3.\1",
-
-            # 5. cond_type_embedding -> cond_type_embed:
-            r"^cond_type_embedding\.(.*)$":
-            r"cond_type_embed.\1",
-
-            # 6. vision_in -> image_embedder mappings:
-            r"^vision_in\.proj\.0\.(.*)$":
-            r"image_embedder.norm_in.\1",
-            r"^vision_in\.proj\.1\.(.*)$":
-            r"image_embedder.linear_1.\1",
-            r"^vision_in\.proj\.3\.(.*)$":
-            r"image_embedder.linear_2.\1",
-            r"^vision_in\.proj\.4\.(.*)$":
-            r"image_embedder.norm_out.\1",
-
-            # 7. double_blocks mapping:
-            r"^double_blocks\.(\d+)\.img_attn_q\.(.*)$":
-            (r"double_blocks.\1.img_attn_qkv.\2", 0, 3),
-            r"^double_blocks\.(\d+)\.img_attn_k\.(.*)$":
-            (r"double_blocks.\1.img_attn_qkv.\2", 1, 3),
-            r"^double_blocks\.(\d+)\.img_attn_v\.(.*)$":
-            (r"double_blocks.\1.img_attn_qkv.\2", 2, 3),
-            r"^double_blocks\.(\d+)\.txt_attn_q\.(.*)$":
-            (r"double_blocks.\1.txt_attn_qkv.\2", 0, 3),
-            r"^double_blocks\.(\d+)\.txt_attn_k\.(.*)$":
-            (r"double_blocks.\1.txt_attn_qkv.\2", 1, 3),
-            r"^double_blocks\.(\d+)\.txt_attn_v\.(.*)$":
-            (r"double_blocks.\1.txt_attn_qkv.\2", 2, 3),
-            r"^double_blocks\.(\d+)\.img_mlp\.fc1\.(.*)$":
-            r"double_blocks.\1.img_mlp.fc_in.\2",
-            r"^double_blocks\.(\d+)\.img_mlp\.fc2\.(.*)$":
-            r"double_blocks.\1.img_mlp.fc_out.\2",
-            r"^double_blocks\.(\d+)\.txt_mlp\.fc1\.(.*)$":
-            r"double_blocks.\1.txt_mlp.fc_in.\2",
-            r"^double_blocks\.(\d+)\.txt_mlp\.fc2\.(.*)$":
-            r"double_blocks.\1.txt_mlp.fc_out.\2",
-
-            # 8. Final layer mapping:
-            r"^final_layer\.adaLN_modulation\.1\.(.*)$":
-            r"final_layer.adaLN_modulation.linear.\1",
-        })
-
-    # Reverse mapping for saving checkpoints: custom -> hf
-    reverse_param_names_mapping: dict = field(default_factory=lambda: {})
-
-    # Parameters from HY-WorldPlay config.json (loaded from checkpoint)
-    patch_size: list | tuple | int = field(default_factory=lambda: [1, 1, 1])
-    # Base latent channels - will be expanded in __post_init__ if concat_condition=True
-    in_channels: int = 32
-    concat_condition: bool = True
-    out_channels: int = 32
-    hidden_size: int = 2048
-    heads_num: int = 16
-    mlp_width_ratio: float = 4.0
-    mlp_act_type: str = "gelu_tanh"
-    mm_double_blocks_depth: int = 54
-    mm_single_blocks_depth: int = 0
-    rope_dim_list: list | tuple = field(default_factory=lambda: [16, 56, 56])
-    qkv_bias: bool = True
-    qk_norm: bool | str = True
-    qk_norm_type: str = "rms"
-    guidance_embed: bool = False
-    use_meanflow: bool = False
-    text_projection: str = "single_refiner"
-    use_attention_mask: bool = True
-    text_states_dim: int = 3584
-    text_states_dim_2: int | None = None
-    text_pool_type: str | None = None
-    rope_theta: float = 256.0
-    attn_mode: str = "flash"
-    attn_param: str | None = None
-    glyph_byT5_v2: bool = True
-    vision_projection: str = "linear"
-    vision_states_dim: int = 1152
-    is_reshape_temporal_channels: bool = False
-    use_cond_type_embedding: bool = True
-    ideal_resolution: str = "480p"
-    ideal_task: str = "i2v"
-    task_type: str = "i2v"
-    exclude_lora_layers: list[str] = field(
-        default_factory=lambda: ["img_in", "txt_in", "time_in", "vector_in"])
-
-    def __post_init__(self):
-        super().__post_init__()
-        # Convert HY-WorldPlay naming to FastVideo naming conventions
-        self.num_attention_heads: int = self.heads_num
-        self.attention_head_dim: int = self.hidden_size // self.heads_num
-        self.num_layers: int = self.mm_double_blocks_depth
-        self.num_single_layers: int = self.mm_single_blocks_depth
-        self.num_refiner_layers: int = 2  # Default for HYWorld
-        self.mlp_ratio: float = float(self.mlp_width_ratio)
-        self.text_embed_dim: int = self.text_states_dim
-        self.text_embed_2_dim: int = self.text_states_dim_2 if self.text_states_dim_2 else 1472
-        self.image_embed_dim: int = self.vision_states_dim
-        self.rope_axes_dim: tuple[int, ...] = tuple(self.rope_dim_list)
-        self.num_channels_latents: int = self.out_channels
-        self.target_size: int = 640
-
-        # Handle concat_condition: when True, actual in_channels = base * 2 + 1
-        # (base latent + condition latent + mask channel)
-        # config.json has base in_channels (32), but img_in needs full (65)
-        if self.concat_condition and self.in_channels == 32:
-            if self.is_reshape_temporal_channels:
-                self.in_channels = self.in_channels + self.in_channels // 2 + 1
-            else:
-                self.in_channels = self.in_channels * 2 + 1  # 32 * 2 + 1 = 65
-
-        # Handle patch_size (can be list/tuple or int)
-        if isinstance(self.patch_size, list | tuple):
-            self.patch_size_t: int = self.patch_size[0]
-            # assume square patch size for height and width
-            patch_size_hw: int = self.patch_size[1]
-            object.__setattr__(self, 'patch_size', patch_size_hw)
-        else:
-            self.patch_size_t = 1
-
-        # Convert qk_norm to string format
-        if isinstance(self.qk_norm, bool):
-            if self.qk_norm:
-                self.qk_norm = "rms_norm" if self.qk_norm_type == "rms" else self.qk_norm_type
-            else:
-                self.qk_norm = "none"
-
-
-@dataclass
-class HYWorldConfig(DiTConfig):
-    arch_config: DiTArchConfig = field(default_factory=HYWorldArchConfig)
-
-    prefix: str = "HYWorld"
@@ -26,6 +26,7 @@ class LongCatVideoArchConfig(DiTArchConfig):
        default_factory=lambda: [is_longcat_blocks])

    # Parameter name mapping for weight conversion
+    # Maps original LongCat third_party names -> native FastVideo names
    param_names_mapping: dict = field(
        default_factory=lambda: {
            # Embedders
@@ -1,84 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""
-LTX-2 Transformer configuration for native FastVideo integration.
-"""
-
-from dataclasses import dataclass, field
-
-from fastvideo.configs.models.dits.base import DiTArchConfig, DiTConfig
-
-
-def is_ltx2_blocks(name: str, _module) -> bool:
-    """FSDP shard condition for LTX-2 transformer blocks."""
-    return "transformer_blocks" in name
-
-
-@dataclass
-class LTX2VideoArchConfig(DiTArchConfig):
-    """Architecture configuration for LTX-2 video transformer."""
-
-    _fsdp_shard_conditions: list = field(
-        default_factory=lambda: [is_ltx2_blocks])
-    _compile_conditions: list = field(default_factory=lambda: [is_ltx2_blocks])
-
-    # Parameter name mapping for weight conversion (hf/comfy -> FastVideo)
-    param_names_mapping: dict = field(
-        default_factory=lambda: {
-            r"^model\.diffusion_model\.(.*)$": r"model.\1",
-            r"^diffusion_model\.(.*)$": r"model.\1",
-            r"^model\.(.*)$": r"model.\1",
-            r"^(.*)$": r"model.\1",
-        })
-
-    reverse_param_names_mapping: dict = field(default_factory=lambda: {})
-    lora_param_names_mapping: dict = field(default_factory=lambda: {})
-
-    # Core transformer settings (defaults from LTX-2 metadata)
-    num_attention_heads: int = 32
-    attention_head_dim: int = 128
-    num_layers: int = 48
-    cross_attention_dim: int = 4096
-    caption_channels: int = 3840
-    norm_eps: float = 1e-6
-    attention_type: str = "default"
-    rope_type: str = "split"
-    double_precision_rope: bool = True
-
-    positional_embedding_theta: float = 10000.0
-    positional_embedding_max_pos: list[int] = field(
-        default_factory=lambda: [20, 2048, 2048])
-    timestep_scale_multiplier: int = 1000
-    use_middle_indices_grid: bool = True
-
-    # Patchification (video-only path)
-    patch_size: tuple[int, int, int] = (1, 1, 1)
-    num_channels_latents: int = 128
-    in_channels: int | None = None
-    out_channels: int | None = None
-
-    # Audio defaults (reserved for joint AV ports)
-    audio_num_attention_heads: int = 32
-    audio_attention_head_dim: int = 64
-    audio_in_channels: int = 128
-    audio_out_channels: int = 128
-    audio_cross_attention_dim: int = 2048
-    audio_positional_embedding_max_pos: list[int] = field(
-        default_factory=lambda: [20])
-    av_ca_timestep_scale_multiplier: int = 1
-
-    def __post_init__(self):
-        super().__post_init__()
-        patch_volume = self.patch_size[0] * self.patch_size[
-            1] * self.patch_size[2]
-        if self.in_channels is None:
-            self.in_channels = self.num_channels_latents * patch_volume
-        if self.out_channels is None:
-            self.out_channels = self.in_channels
-
-
-@dataclass
-class LTX2VideoConfig(DiTConfig):
-    """Main configuration for LTX-2 transformer."""
-
-    arch_config: DiTArchConfig = field(default_factory=LTX2VideoArchConfig)
-    prefix: str = "ltx2"
@@ -1,6 +1,4 @@
 from dataclasses import dataclass, field
-
-import torch
 from fastvideo.configs.models.dits.wanvideo import WanVideoArchConfig, WanVideoConfig


@@ -10,8 +8,8 @@ class MatrixGameWanVideoArchConfig(WanVideoArchConfig):
    # because MatrixGame checkpoints already have patch_embedding.proj format
    param_names_mapping: dict = field(
        default_factory=lambda: {
-            r"^patch_embedding\.(?!proj\.)(.*)$":
-            r"patch_embedding.proj.\1",
+            # Removed: r"^patch_embedding\.(.*)$": r"patch_embedding.proj.\1"
+            # because checkpoint already has correct format
            r"^condition_embedder\.text_embedder\.linear_1\.(.*)$":
            r"condition_embedder.text_embedder.fc_in.\1",
            r"^condition_embedder\.text_embedder\.linear_2\.(.*)$":
@@ -78,14 +76,8 @@ class MatrixGameWanVideoArchConfig(WanVideoArchConfig):
    image_dim: int = 1280


-def _is_transformer_block(param_name: str, module: torch.nn.Module) -> bool:
-    return bool("blocks" in param_name and param_name.split(".")[-1].isdigit())
-
-
@dataclass
 class MatrixGameWanVideoConfig(WanVideoConfig):
    arch_config: MatrixGameWanVideoArchConfig = field(
        default_factory=MatrixGameWanVideoArchConfig)
    prefix: str = "Wan"
-    _compile_conditions: list = field(
-        default_factory=lambda: [_is_transformer_block])
@@ -7,14 +7,10 @@ from fastvideo.configs.models.encoders.clip import (
 from fastvideo.configs.models.encoders.llama import LlamaConfig
 from fastvideo.configs.models.encoders.t5 import T5Config, T5LargeConfig
 from fastvideo.configs.models.encoders.qwen2_5 import Qwen2_5_VLConfig
-from fastvideo.configs.models.encoders.siglip import SiglipVisionConfig
-from fastvideo.configs.models.encoders.reason1 import Reason1ArchConfig, Reason1Config
-from fastvideo.configs.models.encoders.gemma import LTX2GemmaConfig

 __all__ = [
    "EncoderConfig", "TextEncoderConfig", "ImageEncoderConfig",
    "BaseEncoderOutput", "CLIPTextConfig", "CLIPVisionConfig",
    "WAN2_1ControlCLIPVisionConfig", "LlamaConfig", "T5Config", "T5LargeConfig",
-    "Qwen2_5_VLConfig", "Reason1ArchConfig", "Reason1Config", "LTX2GemmaConfig",
-    "SiglipVisionConfig"
+    "Qwen2_5_VLConfig"
 ]
--- a/Show More
+++ b/Show More