add 1333 script

ckpt
Resolve OOM
2026-03-02 21:50:31 +00:00 · 2026-02-09 22:41:25 +00:00 · 2025-11-27 21:08:32 +00:00 · 2025-11-25 09:33:33 +00:00 · 2025-10-13 21:10:34 +00:00 · 2025-10-11 09:58:20 +00:00
253 changed files with 4787 additions and 8907 deletions
@@ -31,9 +31,9 @@ log "Setting up Modal authentication from Buildkite secrets..."
 MODAL_TOKEN_ID=$(buildkite-agent secret get modal_token_id)
 MODAL_TOKEN_SECRET=$(buildkite-agent secret get modal_token_secret)

-# Retrieve other secrets
 WANDB_API_KEY=$(buildkite-agent secret get wandb_api_key)
-HF_API_KEY=$(buildkite-agent secret get hf_api_key)
+
+WANDB_API_KEY=$(buildkite-agent secret get wandb_api_key)

 if [ -n "$MODAL_TOKEN_ID" ] && [ -n "$MODAL_TOKEN_SECRET" ]; then
    log "Retrieved Modal credentials from Buildkite secrets"
@@ -63,15 +63,15 @@ MODAL_ENV="BUILDKITE_REPO=$BUILDKITE_REPO BUILDKITE_COMMIT=$BUILDKITE_COMMIT BUI
 case "$TEST_TYPE" in
    "encoder")
        log "Running encoder tests..."
-        MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_encoder_tests"
+        MODAL_COMMAND="$MODAL_ENV python3 -m modal run $MODAL_TEST_FILE::run_encoder_tests"
        ;;
    "vae")
        log "Running VAE tests..."
-        MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_vae_tests"
+        MODAL_COMMAND="$MODAL_ENV python3 -m modal run $MODAL_TEST_FILE::run_vae_tests"
        ;;
    "transformer")
        log "Running transformer tests..."
-        MODAL_COMMAND="$MODAL_ENV HF_API_KEY=$HF_API_KEY python3 -m modal run $MODAL_TEST_FILE::run_transformer_tests"
+        MODAL_COMMAND="$MODAL_ENV python3 -m modal run $MODAL_TEST_FILE::run_transformer_tests"
        ;;
    "ssim")
        log "Running SSIM tests..."
@@ -1,55 +1,82 @@
-name: Deploy Documentation
+# Sample workflow for building and deploying a Hugo site to GitHub Pages
+name: Deploy FastVideo Docs to Pages

 on:
+  # Runs on pushes targeting the default branch
  push:
-    branches: [ main ]
+    branches:
+      - main
+    paths:
+      - "docs/**/*.md"
+      - "fastvideo/examples/**/*.py"
  pull_request:
-    branches: [ main ]
+    branches: 
+      - main
+    types: [opened, ready_for_review, synchronize, reopened]
+    paths:
+      - "docs/**/*.md"
+      - "fastvideo/examples/**/*.py"

+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
 permissions:
  contents: read
  pages: write
  id-token: write

+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
 concurrency:
  group: "pages"
  cancel-in-progress: false

+# Default to bash
+defaults:
+  run:
+    shell: bash
+
 jobs:
+  pre-commit:
+    uses: ./.github/workflows/pre-commit.yml
+
+  # Build job
  build:
    runs-on: ubuntu-latest
+    needs: pre-commit
    steps:
      - name: Checkout
        uses: actions/checkout@v4
-
-      - name: Setup Python
+      - name: Setup Pages
+        id: pages
+        uses: actions/configure-pages@v5
+      - name: Set up Python
        uses: actions/setup-python@v5
        with:
-          python-version: '3.12'
-
+          python-version: "3.10"
      - name: Install dependencies
        run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements-mkdocs.txt
-
-      - name: Setup Pages
-        uses: actions/configure-pages@v4
-
-      - name: Build documentation
-        run: mkdocs build
-
+          cd docs
+          pip install -r requirements-docs.txt
+      - name: Build docs
+        run: |
+          cd docs
+          make clean
+          make html
      - name: Upload artifact
        uses: actions/upload-pages-artifact@v3
        with:
-          path: ./site
+          path: ./docs/build/html

+  # Deployment job
  deploy:
    environment:
      name: github-pages
      url: ${{ steps.deployment.outputs.page_url }}
+    if: ${{ github.event_name == 'push' }}
    runs-on: ubuntu-latest
    needs: build
-    if: github.ref == 'refs/heads/main'
    steps:
      - name: Deploy to GitHub Pages
        id: deployment
@@ -352,7 +352,7 @@ jobs:
      volume_size: 100
      disk_size: 100
      image: "ghcr.io/${{ github.repository }}/fastvideo-dev:py3.12-latest"
-      test_command: "uv pip install -e .[test] && pytest ./fastvideo/dataset/ -vs && pytest ./fastvideo/workflow/ -vs && pytest ./fastvideo/entrypoints/ -vs"
+      test_command: "uv pip install -e .[test] && pytest ./fastvideo/dataset/ -vs && pytest ./fastvideo/workflow/ -vs"
      timeout_minutes: 30
    secrets:
      RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }}
@@ -14,8 +14,6 @@ wandb/
 *.pt
 cache_dir/
 wandb/
-venv/
-.venv/
 runs/
 samples/
 *validation/
@@ -39,13 +37,12 @@ dist/
 eggs/
 .eggs/

-# MkDocs documentation
-site/
-docs/getting_started/examples/
-docs/inference/examples/
-docs/training/examples/
-docs/distillation/examples/
-!requirements-mkdocs.txt
+# Sphinx documentation
+docs/_build/
+docs/source/getting_started/examples/
+docs/source/inference/examples/
+docs/source/training/examples/
+docs/source/distillation/examples/

 # VSCode
 .vscode/
@@ -64,7 +61,7 @@ docs/distillation/examples/
 !fastvideo/tests/ssim/reference_videos/**/*.mp4

 # Static images
-!docs/assets/images/**/*.png
+!docs/source/_static/images/**/*.png
 !comfyui/assets/**/*.png
 !comfyui/assets/**/*.gif

@@ -7,7 +7,7 @@
 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.html"><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-3csdw1isz-Euq8_Q8~baewG8hxjXs2gQ" target="_blank"> <b>Slack</b> </a> |  🟣💬 <a href="https://ibb.co/tMwknPLY" target="_blank"> <b> WeChat </b> </a> |
+    | 🕹️ <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.html"><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-3csdw1isz-Euq8_Q8~baewG8hxjXs2gQ" target="_blank"> <b>Slack</b> </a> |  🟣💬 <a href="https://ibb.co/q46BbX6" target="_blank"> <b> WeChat </b> </a> |
 </p>

 <div align="center">
@@ -1,18 +0,0 @@
-<svg width="252" height="105" viewBox="0 0 252 105" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M89.4843 55.5457H101.361L87.7028 101H74.638L89.4843 55.5457Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M96.0167 1.00057H112.645L118.583 48.273H104.924L103.737 39.7882H79.9827L67.5117 55.5457H85.3273L43.1638 101H28.3174L22.3789 55.5457H33.6621L38.4129 91.3031L58.604 68.2729H44.3515L96.0167 1.00057ZM100.768 13.1217L87.7028 29.4852H103.143L100.768 13.1217Z" fill="#356CFF"/>
-<path d="M37.2252 1.00057L22.3789 48.273H36.0375L40.7884 30.6974L62.6727 30.6974L69.6727 21.0005L43.7576 21.0004L46.7269 11.9096L77.6727 11.9096L86 1.00057L37.2252 1.00057Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M108.488 55.5457L94.2351 101C94.2351 101 105.518 101 120.959 101C136.399 101 144.078 93.0133 148.276 79.788C152.432 68.0157 153.027 55.5457 136.399 55.5457C119.771 55.5457 108.488 55.5457 108.488 55.5457ZM109.081 90.697L116.802 65.8487C116.802 65.8487 120.959 65.8487 132.242 65.8487C143.525 65.8487 137.586 78.5759 135.211 84.0304C133.307 88.4021 127.491 90.697 122.74 90.697C117.989 90.697 109.081 90.697 109.081 90.697Z" fill="#356CFF"/>
-<path d="M173.188 1.00056L168.625 11.9096C168.625 11.9096 149.386 11.9092 142.525 11.9095C135.664 11.9098 136.586 20.3944 141.337 20.3944H159.747C168.654 20.3944 166.961 33.6899 163.904 38.5761C160.467 44.0675 157.371 48.273 148.463 48.273L125.188 48.273L124 37.97L147.87 37.97C153.808 37.97 156.184 29.4852 151.433 29.4852H131.836C120.142 29.4852 125.897 1.00043 141.337 1.00043L173.188 1.00056Z" fill="#356CFF"/>
-<path d="M179.938 1.00056L175.688 11.9096L191.221 11.9096L179.938 48.273H192.409L203.692 11.9096L219.132 11.9095L223.289 1.00043L179.938 1.00056Z" fill="#356CFF"/>
-<path d="M161.341 55.5457H202.845L198.5 65.8487H169.654L167.279 73.7268H188.5L184.749 82.8177H164.31L161.934 90.697H190.251L186.624 101H146.494L161.341 55.5457Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M230.821 54.9391C255.169 54.9391 251.776 67.0602 249.231 77.9692C246.686 88.8783 240.917 101 217.757 101C194.596 101 195.606 88.8783 199.347 77.9692C203.089 67.0602 206.473 54.9391 230.821 54.9391ZM237.948 77.9692C239.984 70.6965 240.917 65.242 228.446 65.242C215.975 65.242 211.818 71.9087 210.037 77.9692C208.255 84.0298 208.255 91.3025 219.538 91.3025C230.821 91.3025 235.911 85.2419 237.948 77.9692Z" fill="#356CFF"/>
-<path d="M173.188 1.00056L168.625 11.9096C168.625 11.9096 149.386 11.9092 142.525 11.9095C135.664 11.9098 136.586 20.3944 141.337 20.3944M173.188 1.00056C173.188 1.00056 156.777 1.00043 141.337 1.00043M173.188 1.00056L141.337 1.00043M141.337 20.3944C146.088 20.3944 150.839 20.3944 159.747 20.3944M141.337 20.3944H159.747M159.747 20.3944C168.654 20.3944 166.961 33.6899 163.904 38.5761C160.467 44.0675 157.371 48.273 148.463 48.273M148.463 48.273C139.556 48.273 125.188 48.273 125.188 48.273M148.463 48.273L125.188 48.273M125.188 48.273L124 37.97M124 37.97C124 37.97 141.931 37.97 147.87 37.97M124 37.97L147.87 37.97M147.87 37.97C153.808 37.97 156.184 29.4852 151.433 29.4852M151.433 29.4852C146.682 29.4852 138.962 29.4852 131.836 29.4852M151.433 29.4852H131.836M131.836 29.4852C120.142 29.4852 125.897 1.00043 141.337 1.00043M37.2252 1.00057L22.3789 48.273H36.0375L40.7884 30.6974L62.6727 30.6974L69.6727 21.0005L43.7576 21.0004L46.7269 11.9096L77.6727 11.9096L86 1.00057L37.2252 1.00057ZM96.0167 1.00057H112.645L118.583 48.273H104.924L103.737 39.7882H79.9827L67.5117 55.5457H85.3273L43.1638 101H28.3174L22.3789 55.5457H33.6621L38.4129 91.3031L58.604 68.2729H44.3515L96.0167 1.00057ZM87.7028 29.4852L100.768 13.1217L103.143 29.4852H87.7028ZM89.4843 55.5457H101.361L87.7028 101H74.638L89.4843 55.5457ZM108.488 55.5457L94.2351 101C94.2351 101 105.518 101 120.959 101C136.399 101 144.078 93.0133 148.276 79.788C152.432 68.0157 153.027 55.5457 136.399 55.5457C119.771 55.5457 108.488 55.5457 108.488 55.5457ZM116.802 65.8487L109.081 90.697C109.081 90.697 117.989 90.697 122.74 90.697C127.491 90.697 133.307 88.4021 135.211 84.0304C137.586 78.5759 143.525 65.8487 132.242 65.8487C120.959 65.8487 116.802 65.8487 116.802 65.8487ZM179.938 1.00056L175.688 11.9096L191.221 11.9096L179.938 48.273H192.409L203.692 11.9096L219.132 11.9095L223.289 1.00043L179.938 1.00056ZM161.341 55.5457H202.845L198.5 65.8487H169.654L167.279 73.7268H188.5L184.749 82.8177H164.31L161.934 90.697H190.251L186.624 101H146.494L161.341 55.5457ZM230.821 54.9391C255.169 54.9391 251.776 67.0602 249.231 77.9692C246.686 88.8783 240.917 101 217.757 101C194.596 101 195.606 88.8783 199.347 77.9692C203.089 67.0602 206.473 54.9391 230.821 54.9391ZM228.446 65.242C240.917 65.242 239.984 70.6965 237.948 77.9692C235.911 85.2419 230.821 91.3025 219.538 91.3025C208.255 91.3025 208.255 84.0298 210.037 77.9692C211.818 71.9087 215.975 65.242 228.446 65.242Z" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M15.2524 55.5451L21.191 100.999L24.7541 100.999L18.8156 55.5451L15.2524 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M8.12646 55.5451L14.065 100.999L15.2527 100.999L9.31417 55.5451L8.12646 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M1 55.5451L6.93853 100.999L7.53239 100.999L1.59385 55.5451L1 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="0.593853"/>
-<path d="M15.2524 48.2724L30.0988 1H33.6619L18.8156 48.2724H15.2524Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M8.12646 48.2724L22.9728 1H24.1605L9.31417 48.2724H8.12646Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M1 48.2724L15.8463 1H16.4402L1.59385 48.2724H1Z" fill="#356CFF" stroke="#356CFF" stroke-width="0.593853"/>
-<path d="M85.3271 55.5457H67.5116L87 12.7363L44.3513 68.2729H58.6038L43.1636 101L85.3271 55.5457Z" fill="#FDC717" stroke="#FDC717" stroke-width="1.18771" stroke-miterlimit="16"/>
-</svg>
@@ -1,6 +0,0 @@
-<svg width="160" height="93" viewBox="0 0 160 93" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M28.8511 91.66L57.6319 1.86368H64.5394L35.7585 91.66H28.8511Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-<path d="M15.0376 91.66L43.8185 1.86368H46.1209L17.3401 91.66H15.0376Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-<path d="M1.22217 91.66L30.003 1.86366H31.1543L2.3734 91.66H1.22217Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.15122"/>
-<path d="M71.4465 1.86483L42.666 91.6599H69.144L78.3538 58.2746H123.251L129.007 39.855H84.1099L89.866 22.5868H152.032L157.788 1.86483H71.4465Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-</svg>
@@ -72,15 +72,6 @@ We give a demo for 2D STA with window size (6,6) operating on a (10, 10) image.

 https://github.com/user-attachments/assets/f3b6dd79-7b43-4b60-a0fa-3d6495ec5747

-
-## STA Configuration Logic
-Here is a diagram of how the window is configured and passed through the FastVideo pipeline:
-
-<div align="center">
-<img src="../../../docs/assets/images/STA_configuration.png" width="80%"/>
-</div>
-
-
 ## Why is STA Fast?
 2D/3D Sliding Window Attention (SWA) creates many mixed blocks in the attention map. Even though mixed blocks have less output value,a mixed block is significantly slower than a dense block due to the GPU-unfriendly masking operation. 

@@ -0,0 +1,452 @@
+{
+  "data": [
+    {
+      "prompt": "Young man skating with a skateboard on the ramps with graffiti of a park with trees, on a sunny day.", 
+      "image_path": "images/mixkit-boy-skating-with-a-skateboard-in-a-park-with-ramps-34389.png"
+    },
+    {
+      "prompt": "In the midst of the joyous New Year's Eve celebration, the cheerful group of friends, their spirits lifted by the festivities, decides to immortalize the moment with a vibrant snapshot", 
+      "image_path": "images/mixkit-a-cheerful-group-of-friends-celebrate-new-years-eve-and-51525.png"
+    },
+    {
+      "prompt": "A man and a woman playing in a field with grass, during a bright afternoon, while cars pass by in the distance.", 
+      "image_path": "images/mixkit-a-cute-couple-playing-on-the-grass-4688.png"
+    },
+    {
+      "prompt": "Aerial view of a rocky mountain in the forest at a sunny day drone flight footage", 
+      "image_path": "images/mixkit-aerial-view-of-a-rocky-mountain-in-the-forest-50589.png"
+    },
+    {
+      "prompt": "A little girl wearing a pink security helmet and denim overall discovers the art of cycling amidst the serene park, as the camera captures her graceful progress.", 
+      "image_path": "images/mixkit-a-little-girl-cruises-through-the-forest-path-on-her-50088.png"
+    },
+    {
+      "prompt": "Aerial shot of a beach shore with sea waves. Big rocks on the sand at an alone beach.", 
+      "image_path": "images/mixkit-aerial-shot-of-a-beach-with-sea-waves-1087.png"
+    },
+    {
+      "prompt": "Young woman cleaning her house decorated with plants and decorations, while dancing happily to music in her headphones.", 
+      "image_path": "images/mixkit-woman-cleaning-her-house-dancing-happy-43379.png"
+    },
+    {
+      "prompt": "Aerial tour in a meadow surrounded by hills on the horizon, while some birds fly low over a lake.", 
+      "image_path": "images/mixkit-birds-flying-low-over-a-lake-in-a-meadow-41417.png"
+    },
+    {
+      "prompt": "In the video, a lone rider guides a majestic horse across an expansive, open field as the sun sets in the background. The rider, dressed in a classic blue shirt and wide-brimmed hat, sits confidently in the saddle, silhouetted against the warm glow of the evening sky. The horse moves gracefully, its mane and tail flowing with each step, creating a sense of harmony between horse and rider. Surrounding the pair, towering trees form a natural border, their leaves gently rustling in the breeze. The shadows lengthen on the ground, accentuating the serene and timeless feel of the scene. The distant hills and wooden fences frame the horizon, adding depth to the tranquil landscape. A few horses graze peacefully in the background, blending into the pastoral setting. The overall ambiance evokes a sense of calmness and quietude, capturing a perfect moment in the golden light of dusk.", 
+      "image_path": "images/mixkit-a-rancher-riding-a-horse-at-sunset-1143.png"
+    },
+    {
+      "prompt": "In the video, a martial artist dressed in a traditional white uniform with a black belt demonstrates a series of precise movements against a stark black background. The individual gracefully transitions between stances, embodying a sense of focused discipline and control. Each motion is executed with a deliberate pace, showcasing the fluidity of martial arts techniques. The soft lighting creates subtle highlights on the uniform, adding depth to the figure as it moves. The practitioner begins with an open-hand pose, feet firmly grounded, gradually shifting to a powerful forward punch. The fluidity of the sequence displays a mastery of balance and poise. Every trajectory of the limbs is precise and deliberate, capturing the elegance and strength of martial arts. The serene, isolated setting enhances the intensity and concentration of the practitioner. This visual presentation is an elegant interplay of motion and stillness, displaying the art form's discipline and grace.", 
+      "image_path": "images/mixkit-a-young-man-practicing-his-karate-moves-49635.png"
+    },
+    {
+      "prompt": "In a serene and softly lit yoga studio, three individuals engage in a yoga session, each performing an upward-facing stretch. The central figure is a woman with shoulder-length brown hair, dressed in a light cropped top and green leggings, her posture reflecting grace and concentration. To her right, another participant, a woman in a purple outfit, mirrors the pose with equal poise. On her left, a person with a bun focuses intently, supported slightly by yoga blocks beneath their hands. The warm-colored wooden floor contrasts soothingly with the soft pastel mural on the back wall, featuring an abstract design and partial visage of a serene face. Natural light floods the space from a large window on the right, where lush greens peek through, adding an element of tranquility. In the corner of the room, a collection of meditation instruments, including a gong and a Buddha statue, subtly frame the peaceful setting. The mood is calm yet focused, as all three participants are deeply engaged in their practice. The scene combines elements of balance, harmony, and a shared journey towards mindfulness. This depiction captures the essence of a yoga session that blends personal growth with collective experience.", 
+      "image_path": "images/mixkit-small-group-of-people-doing-yoga-together-43730.png"
+    },
+    {
+      "prompt": "In the deep blue expanse of the ocean, two dolphins glide effortlessly, their sleek bodies reflecting the sunlight filtering through the water. The prominent shadows and caustics create a shimmering effect on their skin, capturing the beauty of their natural habitat. Each dolphin moves with a fluid grace, occasionally interacting with gentle nudges, showcasing their playful and social nature. The scene is vibrant and dynamic, with the clear blue background accentuating the dolphins' movements, making it an ideal subject for AI recreation.", 
+      "image_path": "images/mixkit-dolphins-underwater-4133.png"
+    },
+    {
+      "prompt": "A bustling ski slope comes alive with skiers descending a pristine, snow-covered hill, surrounded by towering, snow-draped evergreens. Several figures stand atop the slope, silhouetted against a clear blue sky, preparing to embark on their ski run. The chair lift on the right continuously drops off eager adventurers, adding to the excitement at the hilltop. Each skier, clad in colorful winter gear, carves distinct paths into the textured snow as they weave their way down. The interplay of sunlight and shadows accentuates the myriad tracks etched into the slope, creating a dynamic visual rhythm. The scene captures a vibrant winter wonderland, full of action and the thrill of a perfect ski day.", 
+      "image_path": "images/mixkit-skiers-on-a-snowy-slope-3327.png"
+    },
+    {
+      "prompt": "A determined climber is scaling a massive rock face, showcasing exceptional strength and skill. The person, clad in a teal shirt and dark pants, climbs with precision, their movements measured and deliberate. They are secured by climbing gear, which includes ropes and a harness, emphasizing their commitment to safety. The rugged texture of the sandy-colored rock provides an imposing backdrop, adding drama and scale to the climb. In the distance, other large rock formations and sparse vegetation can be seen under a bright, overcast sky, contributing to the natural and adventurous atmosphere. The scene captures a moment of focus and challenge, highlighting the climber's tenacity and the breathtaking environment.",
+      "image_path": "images/mixkit-alpinist-climbing-a-huge-rock-in-a-desert-43306.png"
+    },
+    {
+      "prompt": "A silver SUV drives along a winding, snow-covered mountain road, with dense pine trees blanketed in snow lining both sides. The scene is serene, with the vehicle moving smoothly, possibly on a winter journey or vacation. As the SUV disappears around the bend, another, darker SUV follows, creating a sense of motion and perspective on the snow-dusted asphalt. The towering, snow-laden rock formation to the right contrasts with the dark green of the pines, highlighting the peacefulness of the wintry landscape.",
+      "image_path": "images/mixkit-curve-on-a-snowy-forest-road-3317.png"
+    },
+    {
+      "prompt": "A solitary boat glides across the expansive, tranquil expanse of a serene lake. The vessel leaves a gentle wake behind, creating delicate ripples across the mirror-like surface. The water appears a rich shade of teal, seamlessly blending with the sky at the horizon. Silhouettes of distant trees are faintly visible, creating a picturesque backdrop that enhances the solitary journey of the boat. The sky is a calm gradient, shifting from soft oranges near the shore to the pale blues above. In the distance, a few slender poles emerge from the water, remnants of an old structure or natural formation. The mood of the scene is one of peace and solitude, with the boat journeying steadily through the quiet landscape. There is a sense of endless possibilities as the boat moves toward the unseen beyond the frame. The simplicity and stillness of the scene invite contemplation and reflection, encapsulating a perfect moment of quietude on the water.",
+      "image_path": "images/mixkit-motorboat-on-a-large-lake-with-turquoise-blue-waters-4996.png"
+    },
+    {
+      "prompt": "Far shot from high behind a beach on a sunny day, with crowds of people everywhere, buildings and hotels behind, and the sea on the horizon as ships cross it.",
+      "image_path": "480P_i2v_mixkit_images/Far shot from high behind a beach on a sunny day, with crowds of people everywhere, buildings and ho.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Skillful cyclist doing a wheelie on a bike while riding through a forest, on a dirt road, surrounded by many trees, in the morning.",
+      "image_path": "480P_i2v_mixkit_images/Skillful cyclist doing a wheelie on a bike while riding through a forest, on a dirt road, surrounded.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Portrait of a man with a mask and fluorescent paint dancing in front of the camera, under a blue party light.",
+      "image_path": "480P_i2v_mixkit_images/Portrait of a man with a mask and fluorescent paint dancing in front of the camera, under a blue par.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Timelapse of a luxury swimming pool in a boutique hotel.",
+      "image_path": "480P_i2v_mixkit_images/Timelapse of a luxury swimming pool in a boutique hotel..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Man dressed in 80's style dances very happily in his kitchen while listening to music on his radio and drinking wine.",
+      "image_path": "480P_i2v_mixkit_images/Man dressed in 80's style dances very happily in his kitchen while listening to music on his radio a.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Romantic couple embracing and looking at each other in the middle of a forest, during a break on a road trip through nature.",
+      "image_path": "480P_i2v_mixkit_images/Romantic couple embracing and looking at each other in the middle of a forest, during a break on a r.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Big city with many big buildings and a big capitol, in a view from a slow drive through the heights in the afternoon.",
+      "image_path": "480P_i2v_mixkit_images/Big city with many big buildings and a big capitol, in a view from a slow drive through the heights .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A man appears in different parts of an abandoned building, standing in the dark, swinging a baseball bat, outside.",
+      "image_path": "480P_i2v_mixkit_images/A man appears in different parts of an abandoned building, standing in the dark, swinging a baseball.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Many small lights out of focus yellow and blue and of different intensities, at night on a blue background.",
+      "image_path": "480P_i2v_mixkit_images/Many small lights out of focus yellow and blue and of different intensities, at night on a blue back.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Pair of jazz musicians performing a song with their saxophone and trombone on an abandoned train.",
+      "image_path": "480P_i2v_mixkit_images/Pair of jazz musicians performing a song with their saxophone and trombone on an abandoned train..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Pair of mountain bikers climbing a slope in the forest covered with rocks, with abundant trees and vegetation around.",
+      "image_path": "480P_i2v_mixkit_images/Pair of mountain bikers climbing a slope in the forest covered with rocks, with abundant trees and v.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A model with cyberpunk makeup poses in front of a neon light circle background.",
+      "image_path": "480P_i2v_mixkit_images/A model with cyberpunk makeup poses in front of a neon light circle background..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Couple of boy and girl walking hand in hand through a meadow among many cows that feed on grass and grass.",
+      "image_path": "480P_i2v_mixkit_images/Couple of boy and girl walking hand in hand through a meadow among many cows that feed on grass and .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Natural coastal relief on a sunny day, with large hills covered with dry grass in an arid climate, in a panoramic aerial view.",
+      "image_path": "480P_i2v_mixkit_images/Natural coastal relief on a sunny day, with large hills covered with dry grass in an arid climate, i.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Young woman lying on her bed, while chatting on her cell phone, in a close-up shot of her hands typing on the phone.",
+      "image_path": "480P_i2v_mixkit_images/Young woman lying on her bed, while chatting on her cell phone, in a close-up shot of her hands typi.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Meadow with a frozen lake in a forest of pines covered in snow and fog.",
+      "image_path": "480P_i2v_mixkit_images/Meadow with a frozen lake in a forest of pines covered in snow and fog..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Aerial shot of buses and cars on the freeway with a cloudy sky in the background.",
+      "image_path": "480P_i2v_mixkit_images/Aerial shot of buses and cars on the freeway with a cloudy sky in the background..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Beautiful countryside meadow during summer with trees, grass and little yellow flowers in the ground on a sunny day.",
+      "image_path": "480P_i2v_mixkit_images/Beautiful countryside meadow during summer with trees, grass and little yellow flowers in the ground.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A man wearing grey shorts jumps rope in a gym, weights and gym equipment in the background.",
+      "image_path": "480P_i2v_mixkit_images/A man wearing grey shorts jumps rope in a gym, weights and gym equipment in the background..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A young woman wearing a black mini skirt, a red sleeveless shirt and a red Santa hat stands on a stage and sings into a microphone. In the background, a guitar player.",
+      "image_path": "480P_i2v_mixkit_images/A young woman wearing a black mini skirt, a red sleeveless shirt and a red Santa hat stands on a sta.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Little baby with a pacifier, playing with a teddy bear, accompanied by his mom, both sitting on a bed, in a close view.",
+      "image_path": "480P_i2v_mixkit_images/Little baby with a pacifier, playing with a teddy bear, accompanied by his mom, both sitting on a be.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A saxophonist wearing a blazer dances while playing a song in a park.",
+      "image_path": "480P_i2v_mixkit_images/A saxophonist wearing a blazer dances while playing a song in a park..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A young woman with short hair wearing pink sunglasses chews gum and makes a bubble gum with the city in the background.",
+      "image_path": "480P_i2v_mixkit_images/A young woman with short hair wearing pink sunglasses chews gum and makes a bubble gum with the city.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "White flowers from a bridal bouquet, with the background out of focus.",
+      "image_path": "480P_i2v_mixkit_images/White flowers from a bridal bouquet, with the background out of focus..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Silhouette of a person looking at an image projected in front, with spectra and light patterns rotating around a center in the background.",
+      "image_path": "480P_i2v_mixkit_images/Silhouette of a person looking at an image projected in front, with spectra and light patterns rotat.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Natural aerial landscape with a relief covered with abundant trees and vegetation and a thick layer of mist.",
+      "image_path": "480P_i2v_mixkit_images/Natural aerial landscape with a relief covered with abundant trees and vegetation and a thick layer .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Boy dancing happily and cheerfully in a room set in the 80s.",
+      "image_path": "480P_i2v_mixkit_images/Boy dancing happily and cheerfully in a room set in the 80s..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Close up video of the legs of a young gymnast woman doing some acrobatics on a balance beam in a dark and empty gym.",
+      "image_path": "480P_i2v_mixkit_images/Close up video of the legs of a young gymnast woman doing some acrobatics on a balance beam in a dar.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Female scientist in a laboratory, with test tube, and more containers, looking through the lens of a microscope.",
+      "image_path": "480P_i2v_mixkit_images/Female scientist in a laboratory, with test tube, and more containers, looking through the lens of a.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Young woman getting makeup done by a professional makeup artist for a winter concept fashion photo shoot.",
+      "image_path": "480P_i2v_mixkit_images/Young woman getting makeup done by a professional makeup artist for a winter concept fashion photo s.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Loving couple sitting on a log on the shore of a lake outside, sharing an affectionate hug.",
+      "image_path": "480P_i2v_mixkit_images/Loving couple sitting on a log on the shore of a lake outside, sharing an affectionate hug..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Small family of father, mother and daughter, walking together through nature in a forest.",
+      "image_path": "480P_i2v_mixkit_images/Small family of father, mother and daughter, walking together through nature in a forest..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Flying over a peninsula covered in bushy trees, while discovering the sea around it, painted a beautiful turquoise blue, on a sunny day.",
+      "image_path": "480P_i2v_mixkit_images/Flying over a peninsula covered in bushy trees, while discovering the sea around it, painted a beaut.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "A woman with long blonde hair wearing a white t-shirt and black bikini bottoms stands on a wooden deck smiling, with the beach and palm trees in the background.",
+      "image_path": "480P_i2v_mixkit_images/A woman with long blonde hair wearing a white t-shirt and black bikini bottoms stands on a wooden de.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "View towards the horizon in a flat desert at night, as the full moon glows brightly red.",
+      "image_path": "480P_i2v_mixkit_images/View towards the horizon in a flat desert at night, as the full moon glows brightly red..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "100 dollar bill thrown in the street seen up close with the background out of focus, while a person arrives, picks it up and walks away.",
+      "image_path": "480P_i2v_mixkit_images/100 dollar bill thrown in the street seen up close with the background out of focus, while a person .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Flying over a forest of abundant trees and vegetation, with a river and a dam, with houses and hills in the surroundings.",
+      "image_path": "480P_i2v_mixkit_images/Flying over a forest of abundant trees and vegetation, with a river and a dam, with houses and hills.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Artistic portrait of a man with his body and face stained with phosphorescent paint that glows with black light in a dark place.",
+      "image_path": "480P_i2v_mixkit_images/Artistic portrait of a man with his body and face stained with phosphorescent paint that glows with .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Aerial view of the calm blue sea made with a drone showing the horizon and the sea.",
+      "image_path": "480P_i2v_mixkit_images/Aerial view of the calm blue sea made with a drone showing the horizon and the sea..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Cars driving on a two way street underneath a tree, with traffic signs, buildings and the sun in the background.",
+      "image_path": "480P_i2v_mixkit_images/Cars driving on a two way street underneath a tree, with traffic signs, buildings and the sun in the.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Face of a young woman, close up portrait",
+      "image_path": "480P_i2v_mixkit_images/Face of a young woman, close up portrait.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Man with his body splattered with fluorescent paint while doing a slow conceptual dance, under a black light in a dark place with colored spotlights around.",
+      "image_path": "480P_i2v_mixkit_images/Man with his body splattered with fluorescent paint while doing a slow conceptual dance, under a bla.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Two women dressed in colorful retro styles, having fun taking photos in a room with lots of pastel colors.",
+      "image_path": "480P_i2v_mixkit_images/Two women dressed in colorful retro styles, having fun taking photos in a room with lots of pastel c.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "The silhouette of a person who moves his head reflects inside a city with tall buildings next to a lake.",
+      "image_path": "480P_i2v_mixkit_images/The silhouette of a person who moves his head reflects inside a city with tall buildings next to a l.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "View from a car window of the trees lining the road speeding by, with the dazzling sunlight in the sky, in a retro looking video.",
+      "image_path": "480P_i2v_mixkit_images/View from a car window of the trees lining the road speeding by, with the dazzling sunlight in the s.jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Aerial view of two people on a tennis court playing tennis.",
+      "image_path": "480P_i2v_mixkit_images/Aerial view of two people on a tennis court playing tennis..jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "View from the floor upwards of a young woman with long dark hair dancing slowly in green and purple neon lights",
+      "image_path": "480P_i2v_mixkit_images/View from the floor upwards of a young woman with long dark hair dancing slowly in green and purple .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    },
+    {
+      "prompt": "Some friends dancing and having fun together in circles, at a party surrounded by colored lights at a party, in a fancy old place, in a view from below them.",
+      "image_path": "480P_i2v_mixkit_images/Some friends dancing and having fun together in circles, at a party surrounded by colored lights at .jpg",
+      "num_inference_steps": 3,
+      "height": 448,
+      "width": 832,
+      "num_frames": 61
+    }
+  ]
+}
@@ -1,80 +0,0 @@
-FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu22.04
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-SHELL ["/bin/bash", "-c"]
-
-WORKDIR /FastVideo
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    wget \
-    git \
-    ca-certificates \
-    openssh-server \
-    zsh \
-    vim \
-    curl \
-    gcc-11 \
-    g++-11 \
-    clang-11 \
-    && rm -rf /var/lib/apt/lists/*
-
-# Set up C++20 compilers for ThunderKittens
-RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
-
-# Set CUDA environment variables
-ENV CUDA_HOME=/usr/local/cuda-12.8
-ENV PATH=${CUDA_HOME}/bin:${PATH}
-ENV LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
-
-# Install Miniconda and create conda environment
-COPY Miniconda3-latest-Linux-x86_64.sh /tmp/miniconda.sh
-RUN bash /tmp/miniconda.sh -b -p /opt/conda && rm /tmp/miniconda.sh
-ENV PATH=/opt/conda/bin:${PATH}
-RUN /opt/conda/bin/conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main
-RUN /opt/conda/bin/conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r
-RUN /opt/conda/bin/conda update -y -n base conda && \
-    /opt/conda/bin/conda create -y -n fastvideo python=3.12 && \
-    /opt/conda/bin/conda clean -afy
-ENV PATH=/opt/conda/envs/fastvideo/bin:/opt/conda/bin:${PATH}
-
-# Copy just the pyproject.toml first to leverage Docker cache
-COPY pyproject.toml ./
-
-# Create a dummy README to satisfy the installation
-RUN echo "# Placeholder" > README.md
-
-# Install project dependencies inside the conda environment
-RUN source /opt/conda/etc/profile.d/conda.sh && \
-    conda activate fastvideo && \
-    pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir .[dev] && \
-    pip install --no-cache-dir flash-attn==2.8.3 --no-build-isolation
-
-COPY . .
-
-# Install dependencies using pip inside conda env and set up shell configuration
-RUN source /opt/conda/etc/profile.d/conda.sh && \
-    conda activate fastvideo && \
-    pip install --no-cache-dir -e .[dev] && \
-    git config --unset-all http.https://github.com/.extraheader || true && \
-    echo 'source /opt/conda/etc/profile.d/conda.sh && conda activate fastvideo' >> /root/.bashrc && \
-    echo 'if [ -n "$ZSH_VERSION" ] && [ -f ~/.zshrc ]; then . ~/.zshrc; elif [ -f ~/.bashrc ]; then . ~/.bashrc; fi' > /root/.profile
-
-# Install STA (Sliding Tile Attention)
-RUN source /opt/conda/etc/profile.d/conda.sh && \
-    conda activate fastvideo && \
-    cd csrc/attn/sliding_tile_attn && \
-    git submodule update --init --recursive && \
-    python setup.py install
-
-# Install VSA 
-RUN source /opt/conda/etc/profile.d/conda.sh && \
-    conda activate fastvideo && \
-    cd csrc/attn/video_sparse_attn && \
-    git submodule update --init --recursive && \
-    python setup.py install
-
-EXPOSE 22
-
-ENTRYPOINT ["/bin/bash", "-lc", "source /opt/conda/etc/profile.d/conda.sh && conda activate fastvideo && exec /FastVideo/examples/inference/gradio/start.sh"]
@@ -0,0 +1,26 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+clean:
+	@$(SPHINXBUILD) -M clean "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	rm -rf "$(SOURCEDIR)/getting_started/examples"
+	rm -rf "$(SOURCEDIR)/inference/examples"
+	rm -rf "$(SOURCEDIR)/training/examples"
@@ -1,39 +1,20 @@
-# FastVideo Documentation
+# FastVideo documents

-This directory contains the FastVideo documentation built with MkDocs.
-
-## Build the docs locally
+## Build the docs

 ```bash
-# Install dependencies
-pip install -r docs/requirements-mkdocs.txt
+# Install dependencies.
+pip install -r requirements-docs.txt

-# Serve docs with live reload (recommended for development)
-mkdocs serve
-
-# Or build static site
-mkdocs build
+# Build the docs.
+make clean
+make html
 ```

-## View the docs
-
-### Development server (with live reload)
+## Open the docs with your browser

 ```bash
-mkdocs serve
+python -m http.server -d build/html/
 ```

-Then open your browser to: http://127.0.0.1:8000
-
-### Static build
-
-```bash
-mkdocs build
-python -m http.server -d site/
-```
-
-Then open your browser to: http://localhost:8000
-
-## Automatic Deployment
-
-Documentation is automatically built and deployed to GitHub Pages when changes are pushed to the `main` branch via the `.github/workflows/docs.yml` workflow.
+Launch your browser and open localhost:8000.
@@ -1,248 +0,0 @@
-# FastVideo API Reference
-
-This page contains the complete API reference for the FastVideo library.
-
-## fastvideo
-
-### Modules
-
-| Name | Description |
-|------|-------------|
-| [attention](#fastvideoattention) | Attention mechanisms and backends for video generation |
-| [configs](#fastvideoconfigs) | Configuration classes for pipelines, models, and sampling |
-| [distributed](#fastvideodistributed) | Distributed execution and communication utilities |
-| [entrypoints](#fastvideoentrypoints) | Main API entry points for video generation |
-| [models](#fastvideomodels) | Model implementations (transformers, VAEs, schedulers) |
-| [pipelines](#fastvideopipelines) | Core pipeline classes for video diffusion |
-| [training](#fastvideotraining) | Training utilities and helpers |
-| [workflow](#fastvideoworkflow) | Workflow management and orchestration |
-| [dataset](#fastvideodataset) | Dataset handling and preprocessing |
-| [layers](#fastvideolayers) | Custom neural network layers |
-| [platforms](#fastvideoplatforms) | Platform-specific implementations |
-| [utils](#fastvideoutils) | Utility functions and helpers |
-| [worker](#fastvideoworker) | Execution workers for video generation |
-
-## fastvideo.attention
-
-::: fastvideo.attention
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.configs
-
-::: fastvideo.configs
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-### Submodules
-
-#### fastvideo.configs.pipelines
-
-::: fastvideo.configs.pipelines
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.configs.models
-
-::: fastvideo.configs.models
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.configs.sample
-
-::: fastvideo.configs.sample
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-## fastvideo.distributed
-
-::: fastvideo.distributed
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.entrypoints
-
-::: fastvideo.entrypoints
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.models
-
-::: fastvideo.models
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-### Submodules
-
-#### fastvideo.models.registry
-
-::: fastvideo.models.registry
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.models.loader
-
-::: fastvideo.models.loader
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-## fastvideo.pipelines
-
-::: fastvideo.pipelines
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-### Submodules
-
-#### fastvideo.pipelines.composed_pipeline_base
-
-::: fastvideo.pipelines.composed_pipeline_base
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.pipelines.lora_pipeline
-
-::: fastvideo.pipelines.lora_pipeline
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.pipelines.pipeline_batch_info
-
-::: fastvideo.pipelines.pipeline_batch_info
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.pipelines.pipeline_registry
-
-::: fastvideo.pipelines.pipeline_registry
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-#### fastvideo.pipelines.stages
-
-::: fastvideo.pipelines.stages
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 4
-
-## fastvideo.training
-
-::: fastvideo.training
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.workflow
-
-::: fastvideo.workflow
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.dataset
-
-::: fastvideo.dataset
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.layers
-
-::: fastvideo.layers
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.platforms
-
-::: fastvideo.platforms
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
-
-## fastvideo.utils
-
-::: fastvideo.utils
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      heading_level: 3
-
-## fastvideo.worker
-
-::: fastvideo.worker
-    options:
-      show_source: true
-      show_root_heading: true
-      show_root_toc_entry: true
-      show_submodules: true
-      heading_level: 3
@@ -1,27 +0,0 @@
-# API Summary
-
-This page provides a quick overview of the main FastVideo API components.
-
-## Video Generator
-
-::: fastvideo.VideoGenerator
-    options:
-      show_root_heading: false
-      show_source: false
-      heading_level: 3
-
-## Initialization Configuration
-
-::: fastvideo.PipelineConfig
-    options:
-      show_root_heading: false
-      show_source: false
-      heading_level: 3
-
-## Sampling Configuration
-
-::: fastvideo.SamplingParam
-    options:
-      show_root_heading: false
-      show_source: false
-      heading_level: 3
@@ -1,41 +0,0 @@
-.vertical-table-header th.head:not(.stub) {
-    writing-mode: sideways-lr;
-    white-space: nowrap;
-    max-width: 0;
-    p {
-       margin: 0;
-    }
-}
-
-/* Image sizing classes */
-.image-small {
-    max-width: 200px;
-    height: auto;
-}
-
-.image-medium {
-    max-width: 400px;
-    height: auto;
-}
-
-.image-large {
-    max-width: 600px;
-    height: auto;
-}
-
-.image-full {
-    max-width: 100%;
-    height: auto;
-}
-
-/* Responsive images */
-img {
-    max-width: 100%;
-    height: auto;
-}
-
-/* Center images */
-.image-center {
-    display: block;
-    margin: 0 auto;
-}
@@ -1,6 +0,0 @@
-<svg width="160" height="93" viewBox="0 0 160 93" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M28.8511 91.66L57.6319 1.86368H64.5394L35.7585 91.66H28.8511Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-<path d="M15.0376 91.66L43.8185 1.86368H46.1209L17.3401 91.66H15.0376Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-<path d="M1.22217 91.66L30.003 1.86366H31.1543L2.3734 91.66H1.22217Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.15122"/>
-<path d="M71.4465 1.86483L42.666 91.6599H69.144L78.3538 58.2746H123.251L129.007 39.855H84.1099L89.866 22.5868H152.032L157.788 1.86483H71.4465Z" fill="#356CFF" stroke="#356CFF" stroke-width="2.30244"/>
-</svg>
@@ -1,18 +0,0 @@
-<svg width="252" height="105" viewBox="0 0 252 105" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M89.4843 55.5457H101.361L87.7028 101H74.638L89.4843 55.5457Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M96.0167 1.00057H112.645L118.583 48.273H104.924L103.737 39.7882H79.9827L67.5117 55.5457H85.3273L43.1638 101H28.3174L22.3789 55.5457H33.6621L38.4129 91.3031L58.604 68.2729H44.3515L96.0167 1.00057ZM100.768 13.1217L87.7028 29.4852H103.143L100.768 13.1217Z" fill="#356CFF"/>
-<path d="M37.2252 1.00057L22.3789 48.273H36.0375L40.7884 30.6974L62.6727 30.6974L69.6727 21.0005L43.7576 21.0004L46.7269 11.9096L77.6727 11.9096L86 1.00057L37.2252 1.00057Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M108.488 55.5457L94.2351 101C94.2351 101 105.518 101 120.959 101C136.399 101 144.078 93.0133 148.276 79.788C152.432 68.0157 153.027 55.5457 136.399 55.5457C119.771 55.5457 108.488 55.5457 108.488 55.5457ZM109.081 90.697L116.802 65.8487C116.802 65.8487 120.959 65.8487 132.242 65.8487C143.525 65.8487 137.586 78.5759 135.211 84.0304C133.307 88.4021 127.491 90.697 122.74 90.697C117.989 90.697 109.081 90.697 109.081 90.697Z" fill="#356CFF"/>
-<path d="M173.188 1.00056L168.625 11.9096C168.625 11.9096 149.386 11.9092 142.525 11.9095C135.664 11.9098 136.586 20.3944 141.337 20.3944H159.747C168.654 20.3944 166.961 33.6899 163.904 38.5761C160.467 44.0675 157.371 48.273 148.463 48.273L125.188 48.273L124 37.97L147.87 37.97C153.808 37.97 156.184 29.4852 151.433 29.4852H131.836C120.142 29.4852 125.897 1.00043 141.337 1.00043L173.188 1.00056Z" fill="#356CFF"/>
-<path d="M179.938 1.00056L175.688 11.9096L191.221 11.9096L179.938 48.273H192.409L203.692 11.9096L219.132 11.9095L223.289 1.00043L179.938 1.00056Z" fill="#356CFF"/>
-<path d="M161.341 55.5457H202.845L198.5 65.8487H169.654L167.279 73.7268H188.5L184.749 82.8177H164.31L161.934 90.697H190.251L186.624 101H146.494L161.341 55.5457Z" fill="#356CFF"/>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M230.821 54.9391C255.169 54.9391 251.776 67.0602 249.231 77.9692C246.686 88.8783 240.917 101 217.757 101C194.596 101 195.606 88.8783 199.347 77.9692C203.089 67.0602 206.473 54.9391 230.821 54.9391ZM237.948 77.9692C239.984 70.6965 240.917 65.242 228.446 65.242C215.975 65.242 211.818 71.9087 210.037 77.9692C208.255 84.0298 208.255 91.3025 219.538 91.3025C230.821 91.3025 235.911 85.2419 237.948 77.9692Z" fill="#356CFF"/>
-<path d="M173.188 1.00056L168.625 11.9096C168.625 11.9096 149.386 11.9092 142.525 11.9095C135.664 11.9098 136.586 20.3944 141.337 20.3944M173.188 1.00056C173.188 1.00056 156.777 1.00043 141.337 1.00043M173.188 1.00056L141.337 1.00043M141.337 20.3944C146.088 20.3944 150.839 20.3944 159.747 20.3944M141.337 20.3944H159.747M159.747 20.3944C168.654 20.3944 166.961 33.6899 163.904 38.5761C160.467 44.0675 157.371 48.273 148.463 48.273M148.463 48.273C139.556 48.273 125.188 48.273 125.188 48.273M148.463 48.273L125.188 48.273M125.188 48.273L124 37.97M124 37.97C124 37.97 141.931 37.97 147.87 37.97M124 37.97L147.87 37.97M147.87 37.97C153.808 37.97 156.184 29.4852 151.433 29.4852M151.433 29.4852C146.682 29.4852 138.962 29.4852 131.836 29.4852M151.433 29.4852H131.836M131.836 29.4852C120.142 29.4852 125.897 1.00043 141.337 1.00043M37.2252 1.00057L22.3789 48.273H36.0375L40.7884 30.6974L62.6727 30.6974L69.6727 21.0005L43.7576 21.0004L46.7269 11.9096L77.6727 11.9096L86 1.00057L37.2252 1.00057ZM96.0167 1.00057H112.645L118.583 48.273H104.924L103.737 39.7882H79.9827L67.5117 55.5457H85.3273L43.1638 101H28.3174L22.3789 55.5457H33.6621L38.4129 91.3031L58.604 68.2729H44.3515L96.0167 1.00057ZM87.7028 29.4852L100.768 13.1217L103.143 29.4852H87.7028ZM89.4843 55.5457H101.361L87.7028 101H74.638L89.4843 55.5457ZM108.488 55.5457L94.2351 101C94.2351 101 105.518 101 120.959 101C136.399 101 144.078 93.0133 148.276 79.788C152.432 68.0157 153.027 55.5457 136.399 55.5457C119.771 55.5457 108.488 55.5457 108.488 55.5457ZM116.802 65.8487L109.081 90.697C109.081 90.697 117.989 90.697 122.74 90.697C127.491 90.697 133.307 88.4021 135.211 84.0304C137.586 78.5759 143.525 65.8487 132.242 65.8487C120.959 65.8487 116.802 65.8487 116.802 65.8487ZM179.938 1.00056L175.688 11.9096L191.221 11.9096L179.938 48.273H192.409L203.692 11.9096L219.132 11.9095L223.289 1.00043L179.938 1.00056ZM161.341 55.5457H202.845L198.5 65.8487H169.654L167.279 73.7268H188.5L184.749 82.8177H164.31L161.934 90.697H190.251L186.624 101H146.494L161.341 55.5457ZM230.821 54.9391C255.169 54.9391 251.776 67.0602 249.231 77.9692C246.686 88.8783 240.917 101 217.757 101C194.596 101 195.606 88.8783 199.347 77.9692C203.089 67.0602 206.473 54.9391 230.821 54.9391ZM228.446 65.242C240.917 65.242 239.984 70.6965 237.948 77.9692C235.911 85.2419 230.821 91.3025 219.538 91.3025C208.255 91.3025 208.255 84.0298 210.037 77.9692C211.818 71.9087 215.975 65.242 228.446 65.242Z" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M15.2524 55.5451L21.191 100.999L24.7541 100.999L18.8156 55.5451L15.2524 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M8.12646 55.5451L14.065 100.999L15.2527 100.999L9.31417 55.5451L8.12646 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M1 55.5451L6.93853 100.999L7.53239 100.999L1.59385 55.5451L1 55.5451Z" fill="#356CFF" stroke="#356CFF" stroke-width="0.593853"/>
-<path d="M15.2524 48.2724L30.0988 1H33.6619L18.8156 48.2724H15.2524Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M8.12646 48.2724L22.9728 1H24.1605L9.31417 48.2724H8.12646Z" fill="#356CFF" stroke="#356CFF" stroke-width="1.18771"/>
-<path d="M1 48.2724L15.8463 1H16.4402L1.59385 48.2724H1Z" fill="#356CFF" stroke="#356CFF" stroke-width="0.593853"/>
-<path d="M85.3271 55.5457H67.5116L87 12.7363L44.3513 68.2729H58.6038L43.1636 101L85.3271 55.5457Z" fill="#FDC717" stroke="#FDC717" stroke-width="1.18771" stroke-miterlimit="16"/>
-</svg>
@@ -1,53 +0,0 @@
-# Profiling FastVideo
-
-!!! warning
-    Profiling is only intended for FastVideo developers and maintainers to understand the proportion of time spent in different parts of the codebase. **FastVideo end-users should never turn on profiling** as it will significantly slow down the inference.
-
-## Profiling with PyTorch
-
-FastVideo exposes a process-wide torch profiler that you can enable via environment variables. Set `FASTVIDEO_TORCH_PROFILER_DIR` to an absolute directory path to start collecting traces, and specify the regions you want recorded with `FASTVIDEO_TORCH_PROFILE_REGIONS`:
-
-```bash
-FASTVIDEO_TORCH_PROFILER_DIR=/mnt/traces/fastvideo \
-FASTVIDEO_TORCH_PROFILE_REGIONS="profiler_region_model_loading,profiler_region_training_step"
-```
-
-All profiled regions must be registered in `fastvideo.profiler`; the current list includes:
-
- `profiler_region_model_loading` — pipeline/module loading
- `profiler_region_inference_pre_denoising`
- `profiler_region_inference_denoising`
- `profiler_region_inference_post_denoising`
- `profiler_region_training_checkpoint_saving`
- `profiler_region_training_dit`
- `profiler_region_training_validation`
- `profiler_region_training_epoch`
- `profiler_region_training_step`
- `profiler_region_training_backward`
- `profiler_region_training_optimizer`
- `profiler_region_distillation_teacher_forward`
- `profiler_region_distillation_student_forward`
- `profiler_region_distillation_loss`
- `profiler_region_distillation_update`
-
-While profiling is enabled, FastVideo records additional annotations:
-
- `fastvideo.region::<name>` spans are emitted when entering a region.
- `fastvideo.profiler.enable_collection` / `fastvideo.profiler.disable_collection` events mark when torch profiler collection is toggled on or off.
-
-Only one profiler instance is created per process; subsequent pipelines reuse the same controller. If you set `FASTVIDEO_TORCH_PROFILE_REGIONS` incorrectly (e.g. misspelled name), FastVideo logs a warning and ignores that entry.
-
-Additional knobs:
-
- `FASTVIDEO_TORCH_PROFILER_RECORD_SHAPES`
- `FASTVIDEO_TORCH_PROFILER_WITH_PROFILE_MEMORY`
- `FASTVIDEO_TORCH_PROFILER_WITH_STACK`
- `FASTVIDEO_TORCH_PROFILER_WITH_FLOPS`
-
-Traces can be visualized using <https://ui.perfetto.dev/>.
-
-### Best Practices
-
- Keep the profiled step count small; traces can be large and slow down job shutdown while the profiler flushes data.
- After profiling, clean up trace directories to avoid filling disks.
- When adding new regions, register them in `fastvideo.profiler` and wrap the corresponding code block with `with self.profiler_controller.region("your_region"):` or the `@profile_region` decorator.
@@ -1,12 +0,0 @@
-# 💡 Examples
-
-A collection of examples demonstrating usage of FastVideo.
-
-All documented examples are autogenerated using [generate_examples.py](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/generate_examples.py) from examples found in the [examples](https://github.com/hao-ai-lab/FastVideo/tree/main/examples) directory.
-
-## Examples
-
- [Examples Distillation Index](distillation/examples/examples_distillation_index.md)
- [Examples Training Index](training/examples/examples_training_index.md)
- [Examples Inference Index](inference/examples/examples_inference_index.md)
-
@@ -1,41 +0,0 @@
-
-# 🔧 Installation
-
-FastVideo supports the following hardware platforms:
-
- [NVIDIA CUDA](installation/gpu.md)
- [Apple silicon](installation/mps.md)
-
-## Quick Installation
-
-### Using pip
-
-```bash
-pip install fastvideo
-```
-
-### Using conda
-
-```bash
-conda install -c conda-forge fastvideo
-```
-
-### From source
-
-```bash
-git clone https://github.com/hao-ai-lab/FastVideo.git
-cd FastVideo
-pip install -e .
-```
-
-## Hardware Requirements
-
- **NVIDIA GPUs**: CUDA 11.8+ with compute capability 7.0+
- **Apple Silicon**: macOS 12.0+ with M1/M2/M3 chips
- **CPU**: x86_64 architecture (for CPU-only inference)
-
-## Next Steps
-
- [Quick Start Guide](quick_start.md) - Get started with your first video generation
- [Configuration](../inference/configuration.md) - Learn about configuration options
- [Examples](../inference/examples/) - Explore example scripts and notebooks
@@ -1,55 +0,0 @@
-# 🚀 Quick Start
-
-Get up and running with FastVideo in minutes!
-
-## Installation
-
-First, install FastVideo:
-
-```bash
-pip install fastvideo
-```
-
-## Basic Usage
-
-### Text-to-Video Generation
-
-```python
-from fastvideo import FastVideoPipeline
-
-# Initialize the pipeline
-pipe = FastVideoPipeline.from_pretrained("wan2.1-t2v-1.3B")
-
-# Generate a video
-prompt = "A cat playing with a ball of yarn"
-video = pipe(prompt, num_frames=16, height=512, width=512)
-
-# Save the video
-video.save("output.mp4")
-```
-
-### Image-to-Video Generation
-
-```python
-from fastvideo import FastVideoPipeline
-from PIL import Image
-
-# Load an image
-image = Image.open("input.jpg")
-
-# Initialize the pipeline
-pipe = FastVideoPipeline.from_pretrained("wan2.1-i2v-14B-480p")
-
-# Generate a video from the image
-video = pipe(image, num_frames=16, height=480, width=480)
-
-# Save the video
-video.save("output.mp4")
-```
-
-## Next Steps
-
- [Installation Guide](installation.md) - Detailed installation instructions
- [Configuration](../inference/configuration.md) - Learn about configuration options
- [Examples](../inference/examples/) - Explore more examples
- [Optimizations](../inference/optimizations.md) - Performance optimization tips
@@ -1,42 +0,0 @@
-# V1 API
-
-FastVideo's V1 API provides a streamlined interface for video generation tasks with powerful customization options. This page documents the primary components of the API.
-
-## Video Generator
-
-This class will be the primary Python API for generating videos and images.
-
-::: fastvideo.entrypoints.video_generator.VideoGenerator
-    options:
-      show_root_heading: true
-      show_source: false
-      members:
-        - from_pretrained
-      heading_level: 3
-
-`VideoGenerator.from_pretrained()` should be the primary way of creating a new video generator.
-
-## Configuring FastVideo
-
-The following two classes `PipelineConfig` and `SamplingParam` are used to configure initialization and sampling parameters, respectively.
-
-### PipelineConfig
-
-::: fastvideo.configs.pipelines.base.PipelineConfig
-    options:
-      show_root_heading: true
-      show_source: false
-      members:
-        - from_pretrained
-        - dump_to_json
-      heading_level: 4
-
-### SamplingParam
-
-::: fastvideo.configs.sample.base.SamplingParam
-    options:
-      show_root_heading: true
-      show_source: false
-      members:
-        - from_pretrained
-      heading_level: 4
@@ -1,66 +0,0 @@
-# Compatibility Matrix
-
-The table below shows every supported model and optimizations supported for them.
-
-The symbols used have the following meanings:
-
- ✅ = Full compatibility
- ❌ = No compatibility
- ⭕ = Does not apply to this model
-
-## Models x Optimization
-
-The `HuggingFace Model ID` can be directly pass to `from_pretrained()` methods and FastVideo will use the optimal default parameters when initializing and generating videos.
-
-<style>
-  /* Target tables in this section */
-  #models-x-optimization + p + table {
-    display: block;
-    overflow-x: auto;
-    width: 100%;
-    font-size: 0.85rem;
-  }
-  
-  #models-x-optimization + p + table td,
-  #models-x-optimization + p + table th {
-    text-align: center;
-    white-space: nowrap;
-    padding: 0.5em;
-  }
-  
-  /* First two columns can wrap */
-  #models-x-optimization + p + table td:nth-child(1),
-  #models-x-optimization + p + table td:nth-child(2) {
-    white-space: normal;
-    min-width: 120px;
-  }
-  
-  #models-x-optimization + p + table td:nth-child(2) code {
-    font-size: 0.75rem;
-  }
-</style>
-
-| 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.
-
-## Special requirements
-
-### StepVideo T2V
- The self-attention in text-encoder (step_llm) only supports CUDA capabilities sm_80 sm_86 and sm_90
-
-### Sliding Tile Attention
- Currently only Hopper GPUs (H100s) are supported.
@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
@@ -0,0 +1,15 @@
+sphinx==7.4.7
+sphinx-argparse==0.5.2
+sphinx-autodoc2==0.5.0
+sphinx-book-theme==1.1.4
+sphinx-copybutton==0.5.2
+sphinx-design==0.6.1
+sphinx-togglebutton==0.3.2
+myst-parser==3.0.1
+msgspec
+commonmark # Required by sphinx-argparse when using :markdownhelp:
+
+# packages to install to build the documentation
+cachetools
+# -f https://download.pytorch.org/whl/cpu
+torch
@@ -0,0 +1,8 @@
+.vertical-table-header th.head:not(.stub) {
+    writing-mode: sideways-lr;
+    white-space: nowrap;
+    max-width: 0;
+    p {
+       margin: 0;
+    }
+}
@@ -0,0 +1,39 @@
+<style>
+  .notification-bar {
+    width: 100vw;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    font-size: 16px;
+    padding: 0 6px 0 6px;
+  }
+  .notification-bar p {
+    margin: 0;
+  }
+  .notification-bar a {
+    font-weight: bold;
+    text-decoration: none;
+  }
+
+  /* Light mode styles (default) */
+  .notification-bar {
+    background-color: #fff3cd;
+    color: #856404;
+  }
+  .notification-bar a {
+    color: #d97706;
+  }
+
+  /* Dark mode styles */
+  html[data-theme=dark] .notification-bar {
+    background-color: #333;
+    color: #ddd;
+  }
+  html[data-theme=dark] .notification-bar a {
+    color: #ffa500; /* Brighter color for visibility */
+  }
+</style>
+
+<!-- <div class="notification-bar">
+  <p>You are viewing the latest developer preview docs. <a href="https://docs.vllm.ai/en/stable/">Click here</a> to view docs for the latest stable release.</p>
+</div> -->
@@ -0,0 +1,19 @@
+# Summary
+
+## Video Generator
+
+```{autodoc2-summary}
+    fastvideo.VideoGenerator
+```
+
+## Initialization Configuration
+
+```{autodoc2-summary}
+    fastvideo.configs.pipelines.PipelineConfig
+```
+
+## Sampling Configuration
+
+```{autodoc2-summary}
+    fastvideo.configs.sample.SamplingParam
+```
@@ -0,0 +1,22 @@
+# type: ignore
+# SPDX-License-Identifier: Apache-2.0
+from docutils import nodes
+from myst_parser.parsers.sphinx_ import MystParser
+from sphinx.ext.napoleon import docstring
+
+
+class NapoleonParser(MystParser):
+
+    def parse(self, input_string: str, document: nodes.document) -> None:
+        # Get the Sphinx configuration
+        config = document.settings.env.config
+
+        parsed_content = str(
+            docstring.GoogleDocstring(
+                str(docstring.NumpyDocstring(input_string, config)),
+                config,
+            ))
+        return super().parse(parsed_content, document)
+
+
+Parser = NapoleonParser
@@ -0,0 +1,275 @@
+# SPDX-License-Identifier: Apache-2.0
+
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+
+import datetime
+import logging
+import os
+import re
+import sys
+from pathlib import Path
+
+import requests
+
+logger = logging.getLogger(__name__)
+REPO_ROOT = Path(__file__).resolve().parent.parent.parent
+print(os.path.abspath(REPO_ROOT))
+sys.path.append(os.path.abspath(REPO_ROOT))
+
+# -- Project information -----------------------------------------------------
+
+project = 'FastVideo'
+copyright = f'{datetime.datetime.now().year}, FastVideo Team'
+author = 'the FastVideo Team'
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.napoleon",
+    "sphinx.ext.linkcode",
+    "sphinx.ext.intersphinx",
+    "sphinx_copybutton",
+    "autodoc2",
+    "myst_parser",
+    "sphinxarg.ext",
+    "sphinx_design",
+    "sphinx_togglebutton",
+]
+myst_enable_extensions = [
+    "colon_fence",
+    "fieldlist",
+]
+autodoc2_packages = [
+    {
+        "path": "../../fastvideo",
+        "exclude_dirs": ["__pycache__", "third_party"],
+    },
+]
+autodoc2_output_dir = "api"
+autodoc2_render_plugin = "myst"
+autodoc2_hidden_objects = ["dunder", "private", "inherited"]
+autodoc2_docstring_parser_regexes = [
+    (".*", "docs.source.autodoc2_docstring_parser"),
+]
+autodoc2_sort_names = True
+autodoc2_index_template = None
+autodoc2_skip_module_regexes = [
+    "fastvideo.dataset",
+    "fastvideo.distill",
+    "fastvideo.data_preprocess",
+    "fastvideo.models",
+    "fastvideo.sample",
+    "fastvideo.utils",
+    "fastvideo.distill_adv",
+    "fastvideo.train",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns: list[str] = ["**/*.template.md", "**/*.inc.md"]
+
+# Exclude the prompt "$" when copying code
+copybutton_prompt_text = r"\$ "
+copybutton_prompt_is_regexp = True
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_title = project
+html_theme = 'sphinx_book_theme'
+html_logo = '../../assets/logos/icon_simple.svg'
+html_theme_options = {
+    'path_to_docs': 'docs/source',
+    'repository_url': 'https://github.com/hao-ai-lab/FastVideo/',
+    'use_repository_button': True,
+    'use_edit_page_button': True,
+    # Prevents the full API being added to the left sidebar of every page.
+    # Reduces build time by 2.5x and reduces build size from ~225MB to ~95MB.
+    'collapse_navbar': True,
+    # Makes API visible in the right sidebar on API reference pages.
+    'show_toc_level': 3,
+}
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+html_js_files = ["custom.js"]
+html_css_files = ["custom.css"]
+
+myst_url_schemes = {
+    'http': None,
+    'https': None,
+    'mailto': None,
+    'ftp': None,
+    "gh-issue": {
+        "url":
+        "https://github.com/hao-ai-lab/FastVideo/issues/{{path}}#{{fragment}}",
+        "title": "Issue #{{path}}",
+        "classes": ["github"],
+    },
+    "gh-pr": {
+        "url":
+        "https://github.com/hao-ai-lab/FastVideo/pull/{{path}}#{{fragment}}",
+        "title": "Pull Request #{{path}}",
+        "classes": ["github"],
+    },
+    "gh-dir": {
+        "url": "https://github.com/hao-ai-lab/FastVideo/tree/main/{{path}}",
+        "title": "{{path}}",
+        "classes": ["github"],
+    },
+    "gh-file": {
+        "url": "https://github.com/hao-ai-lab/FastVideo/blob/main/{{path}}",
+        "title": "{{path}}",
+        "classes": ["github"],
+    },
+}
+
+# see https://docs.readthedocs.io/en/stable/reference/environment-variables.html # noqa
+READTHEDOCS_VERSION_TYPE = os.environ.get('READTHEDOCS_VERSION_TYPE')
+if READTHEDOCS_VERSION_TYPE == "tag":
+    # remove the warning banner if the version is a tagged release
+    header_file = os.path.join(os.path.dirname(__file__),
+                               "_templates/sections/header.html")
+    # The file might be removed already if the build is triggered multiple times
+    # (readthedocs build both HTML and PDF versions separately)
+    if os.path.exists(header_file):
+        os.remove(header_file)
+
+
+# Generate additional rst documentation here.
+def setup(app):
+    from docs.source.generate_examples import generate_examples
+    generate_examples()
+
+
+_cached_base: str = ""
+_cached_branch: str = ""
+
+
+def get_repo_base_and_branch(pr_number: str) -> tuple[str | None, str | None]:
+    global _cached_base, _cached_branch
+    if _cached_base and _cached_branch:
+        return _cached_base, _cached_branch
+
+    url = f"https://api.github.com/repos/hao-ai-lab/FastVideo/pulls/{pr_number}"
+    response = requests.get(url)
+    if response.status_code == 200:
+        data = response.json()
+        _cached_base = data['head']['repo']['full_name']
+        _cached_branch = data['head']['ref']
+        return _cached_base, _cached_branch
+    else:
+        logger.error("Failed to fetch PR details: %s", response)
+        return None, None
+
+
+def linkcode_resolve(domain, info):
+    if domain != 'py':
+        return None
+    if not info['module']:
+        return None
+
+    # Get path from module name
+    file = Path(f"{info['module'].replace('.', '/')}.py")
+    path = REPO_ROOT / file
+    if not path.exists():
+        path = REPO_ROOT / file.with_suffix("") / "__init__.py"
+    if not path.exists():
+        return None
+
+    # Get the line number of the object
+    with open(path) as f:
+        lines = f.readlines()
+    name = info['fullname'].split(".")[-1]
+    pattern = fr"^( {{4}})*((def|class) )?{name}\b.*"
+    for lineno, line in enumerate(lines, 1):
+        if not line or line.startswith("#"):
+            continue
+        if re.match(pattern, line):
+            break
+
+    # If the line number is not found, return None
+    if lineno == len(lines):
+        return None
+
+    # If the line number is found, create the URL
+    filename = path.relative_to(REPO_ROOT)
+    if "checkouts" in path.parts:
+        # a PR build on readthedocs
+        pr_number = REPO_ROOT.name
+        base, branch = get_repo_base_and_branch(pr_number)
+        if base and branch:
+            return f"https://github.com/{base}/blob/{branch}/{filename}#L{lineno}"
+    # Otherwise, link to the source file on the main branch
+    return f"https://github.com/hao-ai-lab/FastVideo/blob/main/{filename}#L{lineno}"
+
+
+# Mock out external dependencies here, otherwise the autodoc pages may be blank.
+autodoc_mock_imports = [
+    "blake3",
+    "compressed_tensors",
+    "cpuinfo",
+    "cv2",
+    "torch",
+    "huggingface_hub",
+    "torchvision",
+    "transformers",
+    "psutil",
+    "prometheus_client",
+    "sentencepiece",
+    "vllm._C",
+    "PIL",
+    "numpy",
+    'triton',
+    "tqdm",
+    "tensorizer",
+    "pynvml",
+    "outlines",
+    "xgrammar",
+    "librosa",
+    "soundfile",
+    "gguf",
+    "lark",
+    "decord",
+]
+
+for mock_target in autodoc_mock_imports:
+    if mock_target in sys.modules:
+        logger.info(
+            "Potentially problematic mock target (%s) found; "
+            "autodoc_mock_imports cannot mock modules that have already "
+            "been loaded into sys.modules when the sphinx build starts.",
+            mock_target)
+
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
+    "typing_extensions":
+    ("https://typing-extensions.readthedocs.io/en/latest", None),
+    "aiohttp": ("https://docs.aiohttp.org/en/stable", None),
+    "pillow": ("https://pillow.readthedocs.io/en/stable", None),
+    "numpy": ("https://numpy.org/doc/stable", None),
+    "torch": ("https://pytorch.org/docs/stable", None),
+    "psutil": ("https://psutil.readthedocs.io/en/stable", None),
+}
+
+navigation_with_keys = False
@@ -1,4 +1,4 @@
-
+(docker)=
 # 🐳 Using the FastVideo Docker Image

 If you prefer a containerized development environment or want to avoid managing dependencies manually, you can use our prebuilt Docker image:
@@ -3,3 +3,11 @@
 # 🧰 Developer Environment

 Accelerate your FastVideo development workflow by leveraging Docker images and cloud GPUs for efficient experimentation and reproducible environments.
+
+:::{toctree}
+:caption: Contents
+:maxdepth: 1
+
+docker
+runpod
+:::
@@ -1,3 +1,4 @@
+(runpod)=

 # 📦 Developing FastVideo on RunPod

@@ -9,7 +10,7 @@ Choose a GPU that supports CUDA 12.8

 Pick 1 or 2 L40S GPU(s)

-![RunPod CUDA selection](../../assets/images/runpod_cuda.png)
+![RunPod CUDA selection](../../_static/images/runpod_cuda.png)

 When creating your pod template, use this image:

@@ -23,11 +24,11 @@ Paste Container Start Command to support SSH ([RunPod Docs](https://docs.runpod.
 bash -c "apt update;DEBIAN_FRONTEND=noninteractive apt-get install openssh-server -y;mkdir -p ~/.ssh;cd $_;chmod 700 ~/.ssh;echo \"$PUBLIC_KEY\" >> authorized_keys;chmod 700 authorized_keys;service ssh start;sleep infinity"
 ```

-![RunPod template configuration](../../assets/images/runpod_template.png)
+![RunPod template configuration](../../_static/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)
+![RunPod ssh](../../_static/images/runpod_ssh.png)

 ## Working with the pod

@@ -1,3 +1,4 @@
+(developer-overview)=

 # 🛠️ Contributing to FastVideo

@@ -29,6 +29,7 @@ FastVideo separates model components from execution logic with these principles:
 - **Custom Attention Backends**: Components can support and use different Attention implementations
 - **Pipeline Abstraction**: Consistent interface across diffusion models

+(design-fastvideo-args)=
 ## 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.
@@ -60,6 +61,7 @@ with set_current_fastvideo_args(fastvideo_args):
    result = generate_video()
 ```

+(design-pipeline-system)=
 ## Pipeline System

 ### `ComposedPipelineBase`
@@ -106,6 +108,7 @@ def forward(self, batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> Forward
    return batch
 ```

+(design-forwardbatch)=
 ### ForwardBatch

 Defined in `fastvideo/pipelines/pipeline_batch_info.py`, `ForwardBatch` encapsulates the data payload passed between pipeline stages. It typically holds:
@@ -117,10 +120,12 @@ Defined in `fastvideo/pipelines/pipeline_batch_info.py`, `ForwardBatch` encapsul

 This structure facilitates clear state transitions between stages.

+(design-model-components)=
 ## Model Components

 The `fastvideo/models/` directory contains implementations of the core neural network models used in video diffusion:

+(design-transformer-models)=
 ### Transformer Models

 Transformer networks perform the actual denoising during diffusion:
@@ -147,6 +152,7 @@ def forward(
    return noise_pred  # Predicted noise residual
 ```

+(design-vae-variational-auto-encoder)=
 ### VAE (Variational Auto-Encoder)

 VAEs handle conversion between pixel space and latent space:
@@ -164,6 +170,7 @@ FastVideo's VAE implementations include:
 - Optional tiling for large frames
 - Distributed weight support

+(design-text-and-image-encoders)=
 ### Text and Image Encoders

 Encoders process conditioning inputs into embeddings:
@@ -181,6 +188,7 @@ FastVideo implements optimizations such as:
 - Caching for common prompts
 - Precision-tuned computation

+(design-schedulers)=
 ### Schedulers

 Schedulers manage the diffusion sampling process:
@@ -208,6 +216,7 @@ def step(
    return prev_sample
 ```

+(design-optimized-attention)=
 ## Optimized Attention

 The `fastvideo/attention/` directory contains optimized attention implementations crucial for efficient video diffusion:
@@ -236,10 +245,12 @@ Supports various patterns with memory optimization techniques:
 - **Cross/Self/Temporal/Global-Local Attention**
 - Chunking, progressive computation, optimized masking

+(design-distributed-processing)=
 ## Distributed Processing

 The `fastvideo/distributed/` directory contains implementations for distributed model execution:

+(design-tensor-parallelism)=
 ### Tensor Parallelism

 Tensor parallelism splits model weights across devices:
@@ -296,6 +307,7 @@ Efficient communication primitives minimize distributed overhead:
 - **Tensor-Parallel AllReduce**: Combines partial results
 - **Distributed Synchronization**: Coordinates execution

+(design-forwardcontext)=
 ## Forward Context Management

 ### ForwardContext
@@ -318,6 +330,7 @@ with set_forward_context(current_timestep, attn_metadata, fastvideo_args):
    output = model(inputs)
 ```

+(design-executor-and-worker-abstractions)=
 ## Executor and Worker System

 The `fastvideo/worker/` directory contains the distributed execution framework:
@@ -344,6 +357,7 @@ Each GPU worker:

 This design allows FastVideo to efficiently utilize multiple GPUs while providing a simple, unified interface for model execution.

+(design-platforms)=
 ## Platforms

 The `fastvideo/platforms/` directory provides hardware platform abstractions that enable FastVideo to run efficiently on different hardware configurations:
@@ -374,6 +388,7 @@ else:

 The platform system is designed to be extensible for future hardware targets.

+(design-logger)=
 ## Logger
 See [PR](https://github.com/hao-ai-lab/FastVideo/pull/356)

@@ -1,3 +1,4 @@
+(v0-data-preprocess)=

 # 🧱 Data Preprocess for Distillation

@@ -6,11 +6,10 @@ import re
 from dataclasses import dataclass, field
 from pathlib import Path

-ROOT_DIR = Path(__file__).parent.parent.resolve()
-ROOT_DIR_RELATIVE = '../..'
+ROOT_DIR = Path(__file__).parent.parent.parent.resolve()
+ROOT_DIR_RELATIVE = '../../../..'
 EXAMPLE_DIR = ROOT_DIR / "examples"
-EXAMPLE_DOC_DIR = ROOT_DIR / "docs/getting_started/examples"
-GITHUB_REPO = "hao-ai-lab/FastVideo"  # Update this to your repo
+EXAMPLE_DOC_DIR = ROOT_DIR / "docs/source/getting_started/examples"


 def fix_case(text: str) -> str:
@@ -72,16 +71,9 @@ class Index:

    def generate(self) -> str:
        content = f"# {self.title}\n\n{self.description}\n\n"
-        if self.caption:
-            content += f"## {self.caption}\n\n"
-        # Generate a simple list of links for MkDocs
-        for doc in self.documents:
-            # Convert document path to proper link
-            doc_link = doc.replace("\\", "/")
-            # Get just the filename for the link text
-            doc_title = fix_case(Path(doc).stem.replace("_", " ").title())
-            content += f"- [{doc_title}]({doc_link}.md)\n"
-        content += "\n"
+        content += ":::{toctree}\n"
+        content += f":caption: {self.caption}\n:maxdepth: {self.maxdepth}\n"
+        content += "\n".join(self.documents) + "\n:::\n"
        return content


@@ -150,66 +142,30 @@ class Example:
        return fix_case(self.path.stem.replace("_", " ").title())

    def generate(self) -> str:
-        # Create GitHub link to source
-        github_path = str(self.path.relative_to(ROOT_DIR)).replace("\\", "/")
-        github_url = f"https://github.com/{GITHUB_REPO}/blob/main/{github_path}"
-        content = f"**Source:** [{github_path}]({github_url})\n\n"
+        # Convert the path to a relative path from __file__
+        make_relative = lambda path: ROOT_DIR_RELATIVE / path.relative_to(
+            ROOT_DIR)

-        # Add title for code files
-        if self.main_file.suffix != ".md":
+        content = f"Source <gh-file:{self.path.relative_to(ROOT_DIR)}>.\n\n"
+        include = "include" if self.main_file.suffix == ".md" else \
+            "literalinclude"
+        if include == "literalinclude":
            content += f"# {self.title}\n\n"
-
-        # Include main file content
-        if self.main_file.suffix == ".md":
-            # For markdown files, include the content directly
-            with open(self.main_file, encoding='utf-8') as f:
-                content += f.read() + "\n\n"
-        else:
-            # For code files, use code blocks
-            language = self.main_file.suffix[1:] if self.main_file.suffix else ""
-            with open(self.main_file, encoding='utf-8') as f:
-                file_content = f.read()
-            content += f"```{language}\n{file_content}\n```\n\n"
+        content += f":::{{{include}}} {make_relative(self.main_file)}\n"  # type: ignore[no-untyped-call]
+        if include == "literalinclude":
+            content += f":language: {self.main_file.suffix[1:]}\n"
+        content += ":::\n\n"

        if not self.other_files:
            return content

-        content += "## Additional Files\n\n"
-        # Define binary/non-text file extensions to skip
-        binary_extensions = {
-            '.mp4', '.avi', '.mov', '.mkv', '.gif', '.jpg', '.jpeg', '.png',
-            '.webp', '.bmp', '.pdf', '.zip', '.tar', '.gz', '.mp3', '.wav'
-        }
-
+        content += "## Example materials\n\n"
        for file in sorted(self.other_files):
-            # Skip binary files
-            if file.suffix.lower() in binary_extensions:
-                continue
-
-            file_rel_path = file.relative_to(self.path)
-            # Use collapsible admonition syntax for MkDocs
-            content += f"??? note \"{file_rel_path}\"\n\n"
-
-            try:
-                if file.suffix == ".md":
-                    # Include markdown content with indentation
-                    with open(file, encoding='utf-8') as f:
-                        for line in f:
-                            content += f"    {line}"
-                else:
-                    # Include code with proper formatting
-                    language = file.suffix[1:] if file.suffix else ""
-                    with open(file, encoding='utf-8') as f:
-                        file_content = f.read()
-                    # Indent the code block for the admonition
-                    content += f"    ```{language}\n"
-                    for line in file_content.split('\n'):
-                        content += f"    {line}\n"
-                    content += "    ```\n"
-                content += "\n"
-            except UnicodeDecodeError:
-                # Skip files that can't be decoded as UTF-8
-                continue
+            include = "include" if file.suffix == ".md" else "literalinclude"
+            content += f":::{{admonition}} {file.relative_to(self.path)}\n"
+            content += ":class: dropdown\n\n"
+            content += f":::{{{include}}} {make_relative(file)}\n:::\n"  # type: ignore[no-untyped-call]
+            content += ":::\n\n"

        return content

@@ -239,7 +195,7 @@ class NestedStructure:

 def create_category_indices() -> dict[str, Index]:
    """Create category indices with their respective configurations."""
-    main_index_dir = ROOT_DIR / "docs/examples"
+    main_index_dir = ROOT_DIR / "docs/source/examples"
    if not main_index_dir.exists():
        main_index_dir.mkdir(parents=True)

@@ -247,16 +203,17 @@ def create_category_indices() -> dict[str, Index]:
        "inference":
        Index(
            path=ROOT_DIR /
-            "docs/inference/examples/examples_inference_index.md",
+            "docs/source/inference/examples/examples_inference_index.md",
            title="🚀 Examples",
            description=
-            "Inference examples demonstrate how to use FastVideo inference. We recommend starting with [basic.md](basic.md).",
+            "Inference examples demonstrate how to use FastVideo inference. We recommend starting with <project:basic.md>.",
            caption="Examples",
            maxdepth=1,
        ),
        "training":
        Index(
-            path=ROOT_DIR / "docs/training/examples/examples_training_index.md",
+            path=ROOT_DIR /
+            "docs/source/training/examples/examples_training_index.md",
            title="🚀 Examples",
            description=
            "Training examples demonstrate how to use FastVideo training.",
@@ -266,7 +223,7 @@ def create_category_indices() -> dict[str, Index]:
        "distillation":
        Index(
            path=ROOT_DIR /
-            "docs/distillation/examples/examples_distillation_index.md",
+            "docs/source/distillation/examples/examples_distillation_index.md",
            title="🚀 Examples",
            description=
            "Distillation examples demonstrate how to use FastVideo distillation.",
@@ -289,21 +246,9 @@ def find_examples(category_indices: dict[str, Index],
    examples = []
    glob_patterns = ["*.py", "*.md", "*.sh"]

-    # Map category names to actual directory names
-    category_dir_mapping = {
-        "distillation": "distill",  # examples/distill/ -> distillation category
-    }
-
    # Find categorised examples
    for category in category_indices:
-        # Use mapped directory name if available, otherwise use category name
-        dir_name = category_dir_mapping.get(category, category)
-        category_dir = EXAMPLE_DIR / dir_name
-
-        # Skip if directory doesn't exist
-        if not category_dir.exists():
-            continue
-
+        category_dir = EXAMPLE_DIR / category
        globs = [category_dir.glob(pattern) for pattern in glob_patterns]
        for path in itertools.chain(*globs):
            examples.append(Example(path, category))
@@ -334,18 +279,11 @@ def create_nested_structures(
                                                dict[str,
                                                     NestedStructure]]]] = {}

-    # Map category names to actual directory names
-    category_dir_mapping = {
-        "distillation": "distill",
-    }
-
    for example in examples:
        if example.category not in ["training", "distillation"]:
            continue

-        # Use mapped directory name if available
-        dir_name = category_dir_mapping.get(example.category, example.category)
-        category_dir = EXAMPLE_DIR / dir_name
+        category_dir = EXAMPLE_DIR / example.category
        relative_path = example.path.relative_to(category_dir)
        path_parts = relative_path.parts

@@ -477,7 +415,7 @@ def generate_nested_examples(nested_structures: dict[str, dict[str, dict[
            category_index.documents.append(method)


-def generate_examples(generate_main_index: bool = False) -> None:
+def generate_examples(generate_main_index=False):
    """
    Generate example documentation.
    
@@ -491,14 +429,12 @@ def generate_examples(generate_main_index: bool = False) -> None:
    # Create the main examples index only if requested
    examples_index = None
    if generate_main_index:
-        main_index_dir = ROOT_DIR / "docs/examples"
+        main_index_dir = ROOT_DIR / "docs/source/examples"
        examples_index = Index(
            path=main_index_dir / "examples_index.md",
            title="💡 Examples",
            description=
-            "A collection of examples demonstrating usage of FastVideo.\n\n"
-            f"All documented examples are autogenerated using [generate_examples.py](https://github.com/{GITHUB_REPO}/blob/main/docs/generate_examples.py) "
-            f"from examples found in the [examples](https://github.com/{GITHUB_REPO}/tree/main/examples) directory.",
+            "A collection of examples demonstrating usage of FastVideo.\nAll documented examples are autogenerated using <gh-file:docs/source/generate_examples.py> from examples found in <gh-file:examples>.",
            caption="Examples",
            maxdepth=2)

@@ -535,19 +471,3 @@ def generate_examples(generate_main_index: bool = False) -> None:
    if generate_main_index and examples_index:
        with open(examples_index.path, "w+") as f:
            f.write(examples_index.generate())
-
-
-def on_pre_build_hook(config, **kwargs):
-    """
-    MkDocs hook to generate examples before building the documentation.
-    This function is called automatically by the mkdocs-simple-hooks plugin.
-    """
-    print("Generating example documentation...")
-    generate_examples(generate_main_index=True)
-    print("Example documentation generated successfully!")
-
-
-if __name__ == "__main__":
-    print("Generating example documentation...")
-    generate_examples(generate_main_index=True)
-    print("Example documentation generated successfully!")
@@ -0,0 +1,18 @@
+(installation-index)=
+
+# 🔧 Installation
+
+FastVideo supports the following hardware platforms:
+
+:::{toctree}
+:maxdepth: 1
+:hidden:
+
+installation/gpu
+installation/mps
+:::
+
+- <project:installation/gpu.md>
+  - NVIDIA CUDA
+- <project:installation/mps.md>
+  - Apple silicon
@@ -30,8 +30,17 @@ conda create -n fastvideo python=3.12 -y
 conda activate fastvideo
 ```

+:::{note}
+[PyTorch has deprecated the conda release channel](https://github.com/pytorch/pytorch/issues/138506). If you use `conda`, please only use it to create Python environment rather than installing packages.
+:::
+
 #### uv

+:::{tip}
+We highly recommend using `uv` to install FastVideo. In our experience, `uv` speeds up installation by at least 3x.
+Note that you can also use `uv` to install FastVideo in a Conda environment.
+:::
+
 Or you can create a new Python environment using [uv](https://docs.astral.sh/uv/), a very fast Python environment manager. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment using the following command:

 ```console
@@ -31,8 +31,17 @@ conda create -n fastvideo python=3.12.4 -y
 conda activate fastvideo
 ```

+:::{note}
+[PyTorch has deprecated the conda release channel](https://github.com/pytorch/pytorch/issues/138506). If you use `conda`, please only use it to create Python environment rather than installing packages.
+:::
+
 #### uv

+:::{tip}
+We highly recommend using `uv` to install FastVideo. In our experience, `uv` speeds up installation by at least 3x.
+Note that you can also use `uv` to install FastVideo in a Conda environment.
+:::
+
 Or you can create a new Python environment using [uv](https://docs.astral.sh/uv/), a very fast Python environment manager. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment using the following command:

 ```console
@@ -0,0 +1,83 @@
+# V1 API
+
+FastVideo's V1 API provides a streamlined interface for video generation tasks with powerful customization options. This page documents the primary components of the API.
+
+## Video Generator
+
+This class will be the primary Python API for generating videos and images.
+
+```{autodoc2-summary}
+    fastvideo.VideoGenerator
+```
+
+`````{py:class} VideoGenerator(fastvideo_args: fastvideo.fastvideo_args.FastVideoArgs, executor_class: type[fastvideo.worker.executor.Executor], log_stats: bool)
+:canonical: fastvideo.entrypoints.video_generator.VideoGenerator
+
+```{autodoc2-docstring} fastvideo.entrypoints.video_generator.VideoGenerator
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+`VideoGenerator.from_pretrained()` should be the primary way of creating a new video generator.
+
+````{py:method} from_pretrained(model_path: str, device: typing.Optional[str] = None, torch_dtype: typing.Optional[torch.dtype] = None, pipeline_config: typing.Optional[typing.Union[str | fastvideo.configs.pipelines.PipelineConfig]] = None, **kwargs) -> fastvideo.entrypoints.video_generator.VideoGenerator
+:canonical: fastvideo.entrypoints.video_generator.VideoGenerator.from_pretrained
+:classmethod:
+
+```{autodoc2-docstring} fastvideo.entrypoints.video_generator.VideoGenerator.from_pretrained
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+
+## Configuring FastVideo
+
+The follow two classes `PipelineConfig` and `SamplingParam` are used to configure initialization and sampling parameters, respectively.
+
+### PipelineConfig
+```{autodoc2-summary}
+    fastvideo.PipelineConfig
+```
+
+`````{py:class} PipelineConfig
+:canonical: fastvideo.configs.pipelines.base.PipelineConfig
+
+```{autodoc2-docstring} fastvideo.configs.pipelines.base.PipelineConfig
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+````{py:method} from_pretrained(model_path: str) -> fastvideo.configs.pipelines.base.PipelineConfig
+:canonical: fastvideo.configs.pipelines.base.PipelineConfig.from_pretrained
+:classmethod:
+
+```{autodoc2-docstring} fastvideo.configs.pipelines.base.PipelineConfig.from_pretrained
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+
+````{py:method} dump_to_json(file_path: str)
+:canonical: fastvideo.configs.pipelines.base.PipelineConfig.dump_to_json
+
+```{autodoc2-docstring} fastvideo.configs.pipelines.base.PipelineConfig.dump_to_json
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+
+### SamplingParam
+
+```{autodoc2-summary}
+    fastvideo.SamplingParam
+```
+
+`````{py:class} SamplingParam
+:canonical: fastvideo.configs.sample.base.SamplingParam
+
+```{autodoc2-docstring} fastvideo.configs.sample.base.SamplingParam
+:parser: docs.source.autodoc2_docstring_parser
+```
+
+````{py:method} from_pretrained(model_path: str) -> fastvideo.configs.sample.base.SamplingParam
+:canonical: fastvideo.configs.sample.base.SamplingParam.from_pretrained
+:classmethod:
+
+```{autodoc2-docstring} fastvideo.configs.sample.base.SamplingParam.from_pretrained
+:parser: docs.source.autodoc2_docstring_parser
+```
@@ -1,24 +1,30 @@
 # Welcome to FastVideo

-<div style="text-align: center;">
-  <img src="assets/logos/logo.svg" alt="FastVideo" style="width: 60%;" />
-</div>
+:::{figure} ../../assets/logos/logo.svg
+:align: center
+:alt: FastVideo
+:class: no-scaled-link
+:width: 60%
+:::

-<div style="text-align: center;">
-<strong>FastVideo is a unified inference and post-training framework for accelerated video generation.</strong>
-</div>
+:::{raw} html
+<p style="text-align:center">
+<strong>FastVideo is a unified inference and post-training framework for accelerated video generation.
+</strong>
+</p>

-<div style="text-align: center;">
+<p style="text-align:center">
 <script async defer src="https://buttons.github.io/buttons.js"></script>
 <a class="github-button" href="https://github.com/hao-ai-lab/FastVideo/" data-show-count="true" data-size="large" aria-label="Star">Star</a>
 <a class="github-button" href="https://github.com/hao-ai-lab/FastVideo/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
 <a class="github-button" href="https://github.com/hao-ai-lab/FastVideo/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
-</div>
+</p>
+:::

 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.

 <div style="text-align: center;">
-  <img src="assets/images/fastwan.png" style="width: 100%;"/>
+  <img src=_static/images/fastwan.png width="100%"/>
 </div>

 ## Key Features
@@ -36,16 +42,90 @@ FastVideo has the following features:

 ## Documentation

-Welcome to FastVideo! This documentation will help you get started with our unified inference and post-training framework for accelerated video generation.
+% How to start using FastVideo?

-Use the navigation menu on the left to explore different sections:
+:::{toctree}
+:caption: Getting Started
+:maxdepth: 1

- **Getting Started**: Installation and quick start guides
- **Inference**: Learn how to use FastVideo for video generation
- **Training**: Data preprocessing and fine-tuning workflows  
- **Distillation**: Post-training optimization techniques
- **Sliding Tile Attention**: Advanced attention mechanisms
- **Video Sparse Attention**: Efficient attention for video models
- **Design**: Framework architecture and design principles
- **Developer Guide**: Contributing and development setup
- **API Reference**: Complete API documentation
+getting_started/installation
+<!-- getting_started/v1_api -->
+:::
+
+:::{toctree}
+:caption: Inference
+:maxdepth: 1
+
+inference/inference_quick_start
+inference/examples/examples_inference_index
+inference/configuration
+inference/optimizations
+inference/comfyui
+inference/support_matrix
+inference/cli
+inference/add_pipeline
+:::
+
+:::{toctree}
+:caption: Training
+:maxdepth: 1
+
+training/examples/examples_training_index
+training/data_preprocess
+<!-- training/finetune -->
+:::
+
+:::{toctree}
+:caption: Distillation
+:maxdepth: 1
+
+distillation/examples/examples_distillation_index
+distillation/data_preprocess
+distillation/dmd
+:::
+
+% What is STA Kernel?
+
+:::{toctree}
+:caption: Sliding Tile Attention
+:maxdepth: 1
+
+sliding_tile_attention/installation
+sliding_tile_attention/demo
+:::
+
+% What is VSA Kernel?
+
+:::{toctree}
+:caption: Video Sparse Attention
+:maxdepth: 1
+
+video_sparse_attention/installation
+:::
+
+:::{toctree}
+:caption: Design
+:maxdepth: 1
+design/overview
+:::
+
+:::{toctree}
+:caption: Developer Guide
+:maxdepth: 2
+
+contributing/overview
+contributing/developer_env/index
+:::
+
+:::{toctree}
+:caption: API Reference
+:maxdepth: 2
+
+<!-- api/summary -->
+api/fastvideo/fastvideo
+:::
+
+## Indices and tables
+
+- {ref}`genindex`
+- {ref}`modindex`
@@ -1,3 +1,4 @@
+(add-pipeline)=

 # 🏗️ Adding a New Pipeline

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
JerryZhou54	96f3cbd487	add 1333 script	2026-03-02 21:50:31 +00:00
JerryZhou54	4276b0567f	ckpt	2026-02-09 22:41:25 +00:00
JerryZhou54	36515d5b72	Resolve OOM	2025-11-27 21:08:32 +00:00
JerryZhou54	e02f9d8d47	setup training for 14b MoE	2025-11-25 09:33:33 +00:00
JerryZhou54	df7381e2b0	Support sampling from the full timestep range in dmd_forward & faker_score_forward when the output video is only generated by high noise generator	2025-10-13 21:10:34 +00:00
JerryZhou54	de11ea3020	Small runtime error	2025-10-11 09:58:20 +00:00
JerryZhou54	4a527bccf2	Add new add_noise_high logic to support full MoE training	2025-10-11 09:21:08 +00:00
JerryZhou54	dabf87fefa	Add config for 1.3B MoE	2025-10-11 04:18:03 +00:00
JerryZhou54	8996a391a1	Add pred_noise_to_x_bound & add_noise_high	2025-10-11 00:29:31 +00:00
JerryZhou54	fba8b61c4f	Fix MoE recipe and Add 1.3B MoE script	2025-10-08 03:58:07 +00:00
JerryZhou54	55d8c1e5fb	Fix small runtime issues	2025-10-07 05:03:36 +00:00
JerryZhou54	aeb8f2e5ac	Add matthew's timestep change & add real score guidance scale 2	2025-10-06 22:24:44 +00:00
JerryZhou54	f755dd1ad5	Refactor sf distill code	2025-10-05 23:46:35 +00:00
JerryZhou54	256f788d34	checkpoint	2025-10-04 23:56:36 +00:00