docs: migrate Fern docs from fern/ into docs/ (#6206)

Signed-off-by: Jont828 <jt572@cornell.edu>

.github/actions/changed-files/action.yml

@@ -31,9 +31,9 @@ outputs:
   rust:
     description: 'Whether rust files changed'
     value: ${{ steps.filter.outputs.rust_any_modified }}
-  fern:
-    description: 'Whether fern docs files changed'
-    value: ${{ steps.filter.outputs.fern_any_modified }}
+  docs:
+    description: 'Whether docs files changed'
+    value: ${{ steps.filter.outputs.docs_any_modified }}
 
 runs:
   using: "composite"
@@ -89,7 +89,6 @@ runs:
         echo "trtllm: ${{ steps.filter.outputs.trtllm_any_modified }}"
         echo "frontend: ${{ steps.filter.outputs.frontend_any_modified }}"
         echo "rust: ${{ steps.filter.outputs.rust_any_modified }}"
-        echo "fern: ${{ steps.filter.outputs.fern_any_modified }}"
         echo ""
         echo "=== Files Matching Each Filter ==="
         echo "docs: ${{ steps.filter.outputs.docs_all_modified_files }}"
@@ -103,13 +102,12 @@ runs:
         echo "trtllm: ${{ steps.filter.outputs.trtllm_all_modified_files }}"
         echo "frontend: ${{ steps.filter.outputs.frontend_all_modified_files }}"
         echo "rust: ${{ steps.filter.outputs.rust_all_modified_files }}"
-        echo "fern: ${{ steps.filter.outputs.fern_all_modified_files }}"
 
     - name: Check for uncovered files
       shell: bash
       run: |
         # Combine all filter-specific files into one list
-        COVERED_FILES=$(echo "${{ steps.filter.outputs.docs_all_modified_files }} ${{ steps.filter.outputs.examples_all_modified_files }} ${{ steps.filter.outputs.ignore_all_modified_files }} ${{ steps.filter.outputs.ci_all_modified_files }} ${{ steps.filter.outputs.core_all_modified_files }} ${{ steps.filter.outputs.operator_all_modified_files }} ${{ steps.filter.outputs.deploy_all_modified_files }} ${{ steps.filter.outputs.planner_all_modified_files }} ${{ steps.filter.outputs.vllm_all_modified_files }} ${{ steps.filter.outputs.sglang_all_modified_files }} ${{ steps.filter.outputs.trtllm_all_modified_files }} ${{ steps.filter.outputs.frontend_all_modified_files }} ${{ steps.filter.outputs.rust_all_modified_files }} ${{ steps.filter.outputs.fern_all_modified_files }}" | tr ' ' '\n' | grep -v '^$' | sort -u)
+        COVERED_FILES=$(echo "${{ steps.filter.outputs.docs_all_modified_files }} ${{ steps.filter.outputs.examples_all_modified_files }} ${{ steps.filter.outputs.ignore_all_modified_files }} ${{ steps.filter.outputs.ci_all_modified_files }} ${{ steps.filter.outputs.core_all_modified_files }} ${{ steps.filter.outputs.operator_all_modified_files }} ${{ steps.filter.outputs.deploy_all_modified_files }} ${{ steps.filter.outputs.planner_all_modified_files }} ${{ steps.filter.outputs.vllm_all_modified_files }} ${{ steps.filter.outputs.sglang_all_modified_files }} ${{ steps.filter.outputs.trtllm_all_modified_files }} ${{ steps.filter.outputs.frontend_all_modified_files }} ${{ steps.filter.outputs.rust_all_modified_files }}" | tr ' ' '\n' | grep -v '^$' | sort -u)
 
         # Get all modified files
         ALL_FILES=$(echo "${{ steps.filter.outputs.all_all_modified_files }}" | tr ' ' '\n' | grep -v '^$' | sort -u)

.github/filters.yaml

@@ -8,18 +8,18 @@
 #   sglang   -> sglang build and test
 #   trtllm   -> trtllm build and test
 #   frontend -> frontend EPP image build
-#   fern     -> fern docs lint, sync, and version release
+#   docs     -> fern docs lint, sync, and version release (docs/ directory)
 #
 # Filters for coverage only (no CI triggered):
-#   docs, examples, ignore, planner
+#   examples, ignore, planner
 
 all:
   - '**'
 
 docs:
   - 'docs/**'
+  - 'fern/**'
   - '**/*.md'
-  - '**/*.rst'
   - '**/*.txt'
   - '**/.gitignore'
   - '**/.helmignore'
@@ -27,9 +27,6 @@ docs:
   - 'LICENSE'
   - 'CODEOWNERS'
 
-fern:
-  - 'fern/**'
-
 examples:
   - 'recipes/**'
   - 'examples/**'
@@ -101,7 +98,7 @@ operator:
   - *ci
   - 'deploy/operator/**'
   - 'deploy/operator/.*'
-  - 'docs/kubernetes/api_reference.md'
+  - 'docs/pages/kubernetes/api-reference.md'
 
 deploy:
   - '!**/*.md'

.github/workflows/fern-docs.yml

@@ -18,11 +18,11 @@
 # This workflow handles all Fern documentation automation:
 #
 # 1. LINT (PRs): Validates Fern configuration and checks for broken links
-#    - Triggers on pull requests when fern/** files change
+#    - Triggers on pull requests when docs/** files change
 #    - Runs `fern check` and `fern docs broken-links`
 #
-# 2. SYNC vNEXT (push to main): Syncs fern/ from main to docs-website branch
-#    - Triggers on push to main when fern/** files change
+# 2. SYNC vNEXT (push to main): Syncs docs/ from main to docs-website branch
+#    - Triggers on push to main when docs/** files change
 #    - Preserves versioned documentation snapshots on docs-website branch
 #    - Publishes docs to Fern after syncing
 #
@@ -63,7 +63,7 @@ jobs:
     # Skip for tag pushes - version release doesn't need changed-files check
     if: github.ref_type != 'tag'
     outputs:
-      fern: ${{ steps.changes.outputs.fern }}
+      docs: ${{ steps.changes.outputs.docs }}
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -76,7 +76,7 @@ jobs:
           gh_token: ${{ github.token }}
 
   #############################################################################
-  # LINT JOBS - Run on PRs when fern/** files change
+  # LINT JOBS - Run on PRs when docs/** files change
   #############################################################################
 
   fern-check:
@@ -84,7 +84,7 @@ jobs:
     needs: changed-files
     if: |
       github.ref_type != 'tag' &&
-      needs.changed-files.outputs.fern == 'true' &&
+      needs.changed-files.outputs.docs == 'true' &&
       (github.event_name == 'pull_request' || startsWith(github.ref, 'refs/heads/pull-request/'))
     runs-on: ubuntu-latest
     steps:
@@ -100,7 +100,7 @@ jobs:
         run: npm install -g fern-api
 
       - name: Validate Fern configuration
-        working-directory: fern
+        working-directory: docs
         run: fern check
 
   fern-broken-links:
@@ -108,7 +108,7 @@ jobs:
     needs: changed-files
     if: |
       github.ref_type != 'tag' &&
-      needs.changed-files.outputs.fern == 'true' &&
+      needs.changed-files.outputs.docs == 'true' &&
       (github.event_name == 'pull_request' || startsWith(github.ref, 'refs/heads/pull-request/'))
     runs-on: ubuntu-latest
     steps:
@@ -124,11 +124,11 @@ jobs:
         run: npm install -g fern-api
 
       - name: Check for broken links
-        working-directory: fern
+        working-directory: docs
         run: fern docs broken-links
 
   #############################################################################
-  # SYNC vNEXT - Run on push to main when fern/** files change
+  # SYNC vNEXT - Run on push to main when docs/** files change
   #############################################################################
 
   sync-vnext:
@@ -136,7 +136,7 @@ jobs:
     needs: changed-files
     if: |
       github.ref == 'refs/heads/main' &&
-      (needs.changed-files.outputs.fern == 'true' || github.event_name == 'workflow_dispatch') &&
+      (needs.changed-files.outputs.docs == 'true' || github.event_name == 'workflow_dispatch') &&
       (github.event.inputs.tag == '' || github.event.inputs.tag == null)
     runs-on: ubuntu-latest
     steps:
@@ -151,13 +151,13 @@ jobs:
         uses: actions/checkout@v4
         with:
           ref: docs-website
-          path: fern-checkout
+          path: docs-checkout
           fetch-depth: 1
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Setup Git
         run: |
-          cd fern-checkout
+          cd docs-checkout
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"
 
@@ -165,41 +165,41 @@ jobs:
         run: |
           # Sync pages/ directory (vNext content)
           echo "Syncing pages/ from main to docs-website branch..."
-          rm -rf fern-checkout/fern/pages
-          cp -r main-checkout/fern/pages fern-checkout/fern/pages
+          rm -rf docs-checkout/docs/pages
+          cp -r main-checkout/docs/pages docs-checkout/docs/pages
 
           # Sync versions/next.yml (vNext navigation)
           echo "Syncing versions/next.yml from main to docs-website branch..."
-          cp main-checkout/fern/versions/next.yml fern-checkout/fern/versions/next.yml
+          cp main-checkout/docs/versions/next.yml docs-checkout/docs/versions/next.yml
 
           # Sync assets/ directory
           echo "Syncing assets/ from main to docs-website branch..."
-          rm -rf fern-checkout/fern/assets
-          cp -r main-checkout/fern/assets fern-checkout/fern/assets
+          rm -rf docs-checkout/docs/assets
+          cp -r main-checkout/docs/assets docs-checkout/docs/assets
 
           # Sync fern.config.json
           echo "Syncing fern.config.json from main to docs-website branch..."
-          cp main-checkout/fern/fern.config.json fern-checkout/fern/fern.config.json
+          cp main-checkout/docs/fern.config.json docs-checkout/docs/fern.config.json
 
           # Sync .gitignore if it exists
-          if [ -f main-checkout/fern/.gitignore ]; then
-            cp main-checkout/fern/.gitignore fern-checkout/fern/.gitignore
+          if [ -f main-checkout/docs/.gitignore ]; then
+            cp main-checkout/docs/.gitignore docs-checkout/docs/.gitignore
           fi
 
           # Sync convert_callouts.py script
-          if [ -f main-checkout/fern/convert_callouts.py ]; then
-            cp main-checkout/fern/convert_callouts.py fern-checkout/fern/convert_callouts.py
+          if [ -f main-checkout/docs/convert_callouts.py ]; then
+            cp main-checkout/docs/convert_callouts.py docs-checkout/docs/convert_callouts.py
           fi
 
       - name: Convert GitHub callouts to Fern format
         run: |
           echo "Converting GitHub-style callouts to Fern format in pages/..."
-          python3 fern-checkout/fern/convert_callouts.py --dir fern-checkout/fern/pages
+          python3 docs-checkout/docs/convert_callouts.py --dir docs-checkout/docs/pages
           echo "Callout conversion complete."
 
       - name: Update docs.yml preserving versions
         run: |
-          cd fern-checkout/fern
+          cd docs-checkout/docs
 
           # Extract the list of versioned entries from current docs.yml (on docs-website branch)
           # These are entries after "path: ./versions/next.yml"
@@ -209,7 +209,7 @@ jobs:
           VERSION_ENTRIES=$(awk '/- display-name: v/{found=1} found{print; if(/path:/) found=0}' docs.yml)
 
           # Copy docs.yml from main as base
-          cp ../../main-checkout/fern/docs.yml docs.yml
+          cp ../../main-checkout/docs/docs.yml docs.yml
 
           # If we had version entries, append them after the next.yml line
           if [ -n "$VERSION_ENTRIES" ]; then
@@ -229,7 +229,7 @@ jobs:
       - name: Check for changes
         id: changes
         run: |
-          cd fern-checkout
+          cd docs-checkout
           if git diff --quiet && git diff --cached --quiet; then
             echo "has_changes=false" >> $GITHUB_OUTPUT
             echo "No changes detected"
@@ -242,12 +242,12 @@ jobs:
       - name: Commit and push changes
         if: steps.changes.outputs.has_changes == 'true'
         run: |
-          cd fern-checkout
+          cd docs-checkout
 
           git add -A
           git commit -m "docs(fern): sync vNext from main
 
-          Automated sync of fern/ directory from main branch.
+          Automated sync of docs/ directory from main branch.
           Preserves versioned documentation snapshots.
 
           Source commit: ${{ github.sha }}"
@@ -270,7 +270,7 @@ jobs:
         if: steps.changes.outputs.has_changes == 'true'
         env:
           FERN_TOKEN: ${{ secrets.FERN_TOKEN }}
-        working-directory: fern-checkout/fern
+        working-directory: docs-checkout/docs
         run: fern generate --docs
 
   #############################################################################
@@ -317,13 +317,13 @@ jobs:
         run: |
           TAG="${{ steps.version.outputs.tag }}"
 
-          if [ -d "fern/pages-$TAG" ]; then
-            echo "::error::Version $TAG already exists (fern/pages-$TAG directory found)"
+          if [ -d "docs/pages-$TAG" ]; then
+            echo "::error::Version $TAG already exists (docs/pages-$TAG directory found)"
             exit 1
           fi
 
-          if [ -f "fern/versions/$TAG.yml" ]; then
-            echo "::error::Version $TAG already exists (fern/versions/$TAG.yml found)"
+          if [ -f "docs/versions/$TAG.yml" ]; then
+            echo "::error::Version $TAG already exists (docs/versions/$TAG.yml found)"
             exit 1
           fi
 
@@ -338,22 +338,22 @@ jobs:
         run: |
           TAG="${{ steps.version.outputs.tag }}"
 
-          echo "Creating fern/pages-$TAG/ from fern/pages/..."
+          echo "Creating docs/pages-$TAG/ from docs/pages/..."
 
           # Copy current pages/ to pages-vX.Y.Z/
-          cp -r fern/pages "fern/pages-$TAG"
+          cp -r docs/pages "docs/pages-$TAG"
 
-          echo "Created fern/pages-$TAG/"
-          ls -la "fern/pages-$TAG/" | head -20
+          echo "Created docs/pages-$TAG/"
+          ls -la "docs/pages-$TAG/" | head -20
 
       - name: Update GitHub links to 'main' to version tag
         run: |
           TAG="${{ steps.version.outputs.tag }}"
 
-          echo "Updating GitHub links from 'tree/main' to 'tree/$TAG' in fern/pages-$TAG/..."
+          echo "Updating GitHub links from 'tree/main' to 'tree/$TAG' in docs/pages-$TAG/..."
 
           # Find all markdown files and replace tree/main with tree/vX.Y.Z
-          find "fern/pages-$TAG" -name "*.md" -o -name "*.mdx" | while read file; do
+          find "docs/pages-$TAG" -name "*.md" -o -name "*.mdx" | while read file; do
             if grep -q "github.com/ai-dynamo/dynamo/tree/main" "$file"; then
               echo "Updating: $file"
               sed -i "s|github.com/ai-dynamo/dynamo/tree/main|github.com/ai-dynamo/dynamo/tree/$TAG|g" "$file"
@@ -361,7 +361,7 @@ jobs:
           done
 
           # Also update blob/main references (for direct file links)
-          find "fern/pages-$TAG" -name "*.md" -o -name "*.mdx" | while read file; do
+          find "docs/pages-$TAG" -name "*.md" -o -name "*.mdx" | while read file; do
             if grep -q "github.com/ai-dynamo/dynamo/blob/main" "$file"; then
               echo "Updating blob links: $file"
               sed -i "s|github.com/ai-dynamo/dynamo/blob/main|github.com/ai-dynamo/dynamo/blob/$TAG|g" "$file"
@@ -375,19 +375,19 @@ jobs:
           TAG="${{ steps.version.outputs.tag }}"
 
           echo "Converting GitHub-style callouts to Fern format in pages-$TAG/..."
-          python3 fern/convert_callouts.py --dir "fern/pages-$TAG"
+          python3 docs/convert_callouts.py --dir "docs/pages-$TAG"
           echo "Callout conversion complete."
 
       - name: Create version config file
         run: |
           TAG="${{ steps.version.outputs.tag }}"
           VERSION="${{ steps.version.outputs.version }}"
-          VERSION_FILE="fern/versions/$TAG.yml"
+          VERSION_FILE="docs/versions/$TAG.yml"
 
           echo "Creating version config: $VERSION_FILE"
 
           # Copy next.yml as template
-          cp fern/versions/next.yml "$VERSION_FILE"
+          cp docs/versions/next.yml "$VERSION_FILE"
 
           # Update the comment at the top
           sed -i "s/# Navigation structure for Latest version/# Navigation structure for $TAG version/" "$VERSION_FILE"
@@ -403,7 +403,7 @@ jobs:
       - name: Update docs.yml with new version
         run: |
           TAG="${{ steps.version.outputs.tag }}"
-          DOCS_FILE="fern/docs.yml"
+          DOCS_FILE="docs/docs.yml"
 
           echo "Updating $DOCS_FILE to include $TAG..."
 
@@ -433,15 +433,15 @@ jobs:
         run: |
           TAG="${{ steps.version.outputs.tag }}"
 
-          git add "fern/pages-$TAG/"
-          git add "fern/versions/$TAG.yml"
-          git add fern/docs.yml
+          git add "docs/pages-$TAG/"
+          git add "docs/versions/$TAG.yml"
+          git add docs/docs.yml
 
           git commit -m "docs(fern): release version $TAG
 
-          - Created fern/pages-$TAG/ with documentation snapshot
-          - Created fern/versions/$TAG.yml version navigation config
-          - Updated fern/docs.yml to include $TAG in version list
+          - Created docs/pages-$TAG/ with documentation snapshot
+          - Created docs/versions/$TAG.yml version navigation config
+          - Updated docs/docs.yml to include $TAG in version list
 
           Automated by fern-docs workflow
           Source tag: $TAG"
@@ -461,5 +461,5 @@ jobs:
       - name: Publish Docs
         env:
           FERN_TOKEN: ${{ secrets.FERN_TOKEN }}
-        working-directory: ./fern
+        working-directory: ./docs
         run: fern generate --docs

CONTRIBUTING.md

@@ -129,9 +129,9 @@ Issues labeled `good-first-issue` are sized for new contributors. We provide ext
 
 <!-- We were given the feedback that having information on architecture, languages used, etc. would be helpful for external contributors -->
 
-Understanding Dynamo's architecture helps you find where to make changes. For the complete picture, see the [Architecture Documentation](docs/design_docs/architecture.md) and [Support Matrix](docs/reference/support-matrix.md).
+Understanding Dynamo's architecture helps you find where to make changes. For the complete picture, see the [Architecture Documentation](docs/pages/design-docs/architecture.md) and [Support Matrix](docs/pages/reference/support-matrix.md).
 
-![Dynamo Architecture](docs/images/architecture.png)
+![Dynamo Architecture](docs/assets/img/architecture.png)
 
 ### Core Components
 
@@ -148,9 +148,9 @@ Understanding Dynamo's architecture helps you find where to make changes. For th
 
 | Plane | Purpose | Documentation |
 |-------|---------|---------------|
-| **Discovery Plane** | Service registration and discovery across components | [docs/design_docs/distributed_runtime.md](docs/design_docs/distributed_runtime.md) |
-| **Request Plane** | High-performance request routing between components | [docs/design_docs/request_plane.md](docs/design_docs/request_plane.md) |
-| **KV Event Plane** | KV cache event propagation for cache-aware routing | [docs/design_docs/event_plane.md](docs/design_docs/event_plane.md) |
+| **Discovery Plane** | Service registration and discovery across components | [docs/pages/design-docs/distributed-runtime.md](docs/pages/design-docs/distributed-runtime.md) |
+| **Request Plane** | High-performance request routing between components | [docs/pages/design-docs/request-plane.md](docs/pages/design-docs/request-plane.md) |
+| **KV Event Plane** | KV cache event propagation for cache-aware routing | [docs/pages/design-docs/event-plane.md](docs/pages/design-docs/event-plane.md) |
 
 ### Kubernetes Deployment
 

README.md

@@ -15,14 +15,14 @@ See the License for the specific language governing permissions and
 limitations under the License.
 -->
 
-![Dynamo banner](./docs/images/frontpage-banner.png)
+![Dynamo banner](./docs/assets/img/frontpage-banner.png)
 
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![GitHub Release](https://img.shields.io/github/v/release/ai-dynamo/dynamo)](https://github.com/ai-dynamo/dynamo/releases/latest)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/ai-dynamo/dynamo)
 [![Discord](https://dcbadge.limes.pink/api/server/D92uqZRjCZ?style=flat)](https://discord.gg/D92uqZRjCZ) ![Community Contributors](https://img.shields.io/badge/community_contributors-70%2B-brightgreen)
 
-| **[Roadmap](https://github.com/ai-dynamo/dynamo/issues/5506)** | **[Support Matrix](https://github.com/ai-dynamo/dynamo/blob/main/docs/reference/support-matrix.md)** | **[Docs](https://docs.nvidia.com/dynamo/latest/index.html)** | **[Recipes](https://github.com/ai-dynamo/dynamo/tree/main/recipes)** | **[Examples](https://github.com/ai-dynamo/dynamo/tree/main/examples)** | **[Prebuilt Containers](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/collections/ai-dynamo)** | **[Design Proposals](https://github.com/ai-dynamo/enhancements)** | **[Blogs](https://developer.nvidia.com/blog/tag/nvidia-dynamo)**
+| **[Roadmap](https://github.com/ai-dynamo/dynamo/issues/5506)** | **[Support Matrix](https://github.com/ai-dynamo/dynamo/blob/main/docs/pages/reference/support-matrix.md)** | **[Docs](https://docs.nvidia.com/dynamo/latest/index.html)** | **[Recipes](https://github.com/ai-dynamo/dynamo/tree/main/recipes)** | **[Examples](https://github.com/ai-dynamo/dynamo/tree/main/examples)** | **[Prebuilt Containers](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/collections/ai-dynamo)** | **[Design Proposals](https://github.com/ai-dynamo/enhancements)** | **[Blogs](https://developer.nvidia.com/blog/tag/nvidia-dynamo)**
 
 # NVIDIA Dynamo
 
@@ -31,7 +31,7 @@ High-throughput, low-latency inference framework designed for serving generative
 ## Why Dynamo
 
 <p align="center">
-  <img src="./docs/images/frontpage-gpu-vertical.png" alt="Multi Node Multi-GPU topology" width="600" />
+  <img src="./docs/assets/img/frontpage-gpu-vertical.png" alt="Multi Node Multi-GPU topology" width="600" />
 </p>
 
 Large language models exceed single-GPU capacity. Tensor parallelism spreads layers across GPUs but creates coordination challenges. Dynamo closes this orchestration gap.
@@ -48,25 +48,25 @@ Built in Rust for performance and Python for extensibility, Dynamo is fully open
 
 ## Backend Feature Support
 
-| | [SGLang](docs/backends/sglang/README.md) | [TensorRT-LLM](docs/backends/trtllm/README.md) | [vLLM](docs/backends/vllm/README.md) |
+| | [SGLang](docs/pages/backends/sglang/README.md) | [TensorRT-LLM](docs/pages/backends/trtllm/README.md) | [vLLM](docs/pages/backends/vllm/README.md) |
 |---|:----:|:----------:|:--:|
 | **Best For** | High-throughput serving | Maximum performance | Broadest feature coverage |
-| [**Disaggregated Serving**](docs/design_docs/disagg_serving.md) | ✅ | ✅ | ✅ |
-| [**KV-Aware Routing**](docs/components/router/README.md) | ✅ | ✅ | ✅ |
-| [**SLA-Based Planner**](docs/components/planner/planner_guide.md) | ✅ | ✅ | ✅ |
-| [**KVBM**](docs/components/kvbm/README.md) | 🚧 | ✅ | ✅ |
-| [**Multimodal**](docs/features/multimodal/README.md) | ✅ | ✅ | ✅ |
-| [**Tool Calling**](docs/agents/tool-calling.md) | ✅ | ✅ | ✅ |
+| [**Disaggregated Serving**](docs/pages/design-docs/disagg-serving.md) | ✅ | ✅ | ✅ |
+| [**KV-Aware Routing**](docs/pages/components/router/README.md) | ✅ | ✅ | ✅ |
+| [**SLA-Based Planner**](docs/pages/components/planner/planner-guide.md) | ✅ | ✅ | ✅ |
+| [**KVBM**](docs/pages/components/kvbm/README.md) | 🚧 | ✅ | ✅ |
+| [**Multimodal**](docs/pages/features/multimodal/README.md) | ✅ | ✅ | ✅ |
+| [**Tool Calling**](docs/pages/agents/tool-calling.md) | ✅ | ✅ | ✅ |
 
-> **[Full Feature Matrix →](docs/reference/feature-matrix.md)** — Detailed compatibility including LoRA, Request Migration, Speculative Decoding, and feature interactions.
+> **[Full Feature Matrix →](docs/pages/reference/feature-matrix.md)** — Detailed compatibility including LoRA, Request Migration, Speculative Decoding, and feature interactions.
 
 ## Dynamo Architecture
 
 <p align="center">
-  <img src="./docs/images/frontpage-architecture.png" alt="Dynamo architecture" width="600" />
+  <img src="./docs/assets/img/frontpage-architecture.png" alt="Dynamo architecture" width="600" />
 </p>
 
-> **[Architecture Deep Dive →](docs/design_docs/architecture.md)**
+> **[Architecture Deep Dive →](docs/pages/design-docs/architecture.md)**
 
 ## Latest News
 
@@ -87,7 +87,7 @@ Want to help shape the future of distributed LLM inference? See the **[Contribut
 # Local Quick Start
 
 The following examples require a few system level packages.
-Recommended to use Ubuntu 24.04 with a x86_64 CPU. See [docs/reference/support-matrix.md](docs/reference/support-matrix.md)
+Recommended to use Ubuntu 24.04 with a x86_64 CPU. See [docs/pages/reference/support-matrix.md](docs/pages/reference/support-matrix.md)
 
 ## Install Dynamo
 
@@ -108,7 +108,7 @@ docker run --gpus all --network host --rm -it nvcr.io/nvidia/ai-dynamo/vllm-runt
 
 > **Tip:** To run frontend and worker in the same container, either run processes in background with `&` (see below), or open a second terminal and use `docker exec -it <container_id> bash`.
 
-See [Release Artifacts](docs/reference/release-artifacts.md#container-images) for available versions.
+See [Release Artifacts](docs/pages/reference/release-artifacts.md#container-images) for available versions.
 
 ### Option B: Install from PyPI
 
@@ -143,7 +143,7 @@ pip install torch==2.9.0 torchvision --index-url https://download.pytorch.org/wh
 pip install --pre --extra-index-url https://pypi.nvidia.com "ai-dynamo[trtllm]"
 ```
 
-> **Note:** TensorRT-LLM requires `pip` due to a transitive Git URL dependency that `uv` doesn't resolve. We recommend using the [TensorRT-LLM container](docs/reference/release-artifacts.md#container-images) for broader compatibility.
+> **Note:** TensorRT-LLM requires `pip` due to a transitive Git URL dependency that `uv` doesn't resolve. We recommend using the [TensorRT-LLM container](docs/pages/reference/release-artifacts.md#container-images) for broader compatibility.
 
 **vLLM**
 
@@ -220,7 +220,7 @@ For production deployments on Kubernetes clusters with multiple GPUs.
 ## Prerequisites
 
 - Kubernetes cluster with GPU nodes
-- [Dynamo Platform installed](docs/kubernetes/README.md)
+- [Dynamo Platform installed](docs/pages/kubernetes/README.md)
 - HuggingFace token for model downloads
 
 ## Production Recipes
@@ -346,8 +346,8 @@ python3 -m dynamo.frontend
 
 Dynamo provides comprehensive benchmarking tools:
 
-- **[Benchmarking Guide](docs/benchmarks/benchmarking.md)** – Compare deployment topologies using AIPerf
-- **[SLA-Driven Deployments](docs/components/planner/planner_guide.md)** – Optimize deployments to meet SLA requirements
+- **[Benchmarking Guide](docs/pages/benchmarks/benchmarking.md)** – Compare deployment topologies using AIPerf
+- **[SLA-Driven Deployments](docs/pages/components/planner/planner-guide.md)** – Optimize deployments to meet SLA requirements
 
 ## Frontend OpenAPI Specification
 
@@ -357,11 +357,11 @@ The OpenAI-compatible frontend exposes an OpenAPI 3 spec at `/openapi.json`. To
 cargo run -p dynamo-llm --bin generate-frontend-openapi
 ```
 
-This writes to `docs/reference/api/openapi.json`.
+This writes to `docs/pages/reference/api/openapi.json`.
 
 ## Service Discovery and Messaging
 
-Dynamo uses TCP for inter-component communication. On Kubernetes, native resources ([CRDs + EndpointSlices](docs/kubernetes/service_discovery.md)) handle service discovery. External services are optional for most deployments:
+Dynamo uses TCP for inter-component communication. On Kubernetes, native resources ([CRDs + EndpointSlices](docs/pages/kubernetes/service-discovery.md)) handle service discovery. External services are optional for most deployments:
 
 | Deployment | etcd | NATS | Notes |
 |------------|------|------|-------|
@@ -387,11 +387,11 @@ See [SGLang on Slurm](examples/backends/sglang/slurm_jobs/README.md) and [TRT-LL
 - [10/16] [How Baseten achieved 2x faster inference with NVIDIA Dynamo](https://www.baseten.co/blog/how-baseten-achieved-2x-faster-inference-with-nvidia-dynamo/)
 
 <!-- Reference links for Feature Compatibility Matrix -->
-[disagg]: docs/design_docs/disagg_serving.md
-[kv-routing]: docs/components/router/README.md
-[planner]: docs/components/planner/planner_guide.md
-[kvbm]: docs/components/kvbm/README.md
+[disagg]: docs/pages/design-docs/disagg-serving.md
+[kv-routing]: docs/pages/components/router/README.md
+[planner]: docs/pages/components/planner/planner-guide.md
+[kvbm]: docs/pages/components/kvbm/README.md
 [mm]: examples/multimodal/
-[migration]: docs/fault_tolerance/request_migration.md
+[migration]: docs/pages/fault-tolerance/request-migration.md
 [lora]: examples/backends/vllm/deploy/lora/README.md
-[tools]: docs/agents/tool-calling.md
+[tools]: docs/pages/agents/tool-calling.md

benchmarks/README.md

@@ -20,7 +20,7 @@ This directory contains benchmarking scripts and tools for performance evaluatio
 ## Quick Start
 
 ### Benchmark a Dynamo Deployment
-First, deploy your DynamoGraphDeployment using the [deployment documentation](../docs/kubernetes/), then:
+First, deploy your DynamoGraphDeployment using the [deployment documentation](../docs/pages/kubernetes/), then:
 
 ```bash
 # Port-forward your deployment to http://localhost:8000
@@ -71,4 +71,4 @@ Detailed information is provided in the `prefix_data_generator` directory.
 
 ## Comprehensive Guide
 
-For detailed documentation, configuration options, and advanced usage, see the [complete benchmarking guide](../docs/benchmarks/benchmarking.md).
+For detailed documentation, configuration options, and advanced usage, see the [complete benchmarking guide](../docs/pages/benchmarks/benchmarking.md).

benchmarks/incluster/README.md

-../../docs/benchmarks/benchmarking.md
\ No newline at end of file

benchmarks/profiler/README.md

@@ -6,8 +6,8 @@ SPDX-License-Identifier: Apache-2.0
 
 # Profiler
 
-Documentation for the Dynamo Profiler has moved to [docs/components/profiler/](../../docs/components/profiler/README.md).
+Documentation for the Dynamo Profiler has moved to [docs/pages/components/profiler/](../../docs/pages/components/profiler/README.md).
 
-- [Profiler Overview](../../docs/components/profiler/README.md)
-- [Profiler Guide](../../docs/components/profiler/profiler_guide.md)
-- [Profiler Examples](../../docs/components/profiler/profiler_examples.md)
+- [Profiler Overview](../../docs/pages/components/profiler/README.md)
+- [Profiler Guide](../../docs/pages/components/profiler/profiler-guide.md)
+- [Profiler Examples](../../docs/pages/components/profiler/profiler-examples.md)

benchmarks/profiler/webui/utils.py

@@ -620,7 +620,7 @@ def create_gradio_interface(
 
             > 📝 **Note:** The dotted red line in the prefill and decode charts are default TTFT and ITL SLAs if not specified.
 
-            > ⚠️ **Warning:** The TTFT values here represent the ideal case when requests arrive uniformly, minimizing queueing. Real-world TTFT may be higher than profiling results. To mitigate the issue, planner uses [correction factors](https://github.com/ai-dynamo/dynamo/blob/main/docs/design_docs/planner_design.md#step-2-correction-factor-calculation) to adjust dynamically at runtime.
+            > ⚠️ **Warning:** The TTFT values here represent the ideal case when requests arrive uniformly, minimizing queueing. Real-world TTFT may be higher than profiling results. To mitigate the issue, planner uses [correction factors](https://github.com/ai-dynamo/dynamo/blob/main/docs/pages/design-docs/planner-design.md#step-2-correction-factor-calculation) to adjust dynamically at runtime.
 
             > 💡 **Tip:** Use the GPU cost checkbox and input in the charts section to convert GPU hours to cost.
             """

benchmarks/router/README.md

@@ -127,7 +127,7 @@ To see all available router arguments, run:
 python -m dynamo.frontend --help
 ```
 
-For detailed explanations of router arguments (especially KV cache routing parameters), see the [Router Guide](../../docs/components/router/router_guide.md).
+For detailed explanations of router arguments (especially KV cache routing parameters), see the [Router Guide](../../docs/pages/components/router/router-guide.md).
 
 > [!Note]
 > If you're unsure whether your backend engines correctly emit KV events for certain models (e.g., hybrid models like gpt-oss or nemotron nano 2), use the `--no-kv-events` flag to disable KV event tracking and use approximate KV indexing instead:
@@ -146,7 +146,7 @@ When you launch prefill workers using `run_engines.sh --prefill`, the frontend a
 - Uses the same routing mode as the frontend's `--router-mode` setting
 - Seamlessly integrates with your decode workers for token generation
 
-No additional configuration is needed - simply launch both decode and prefill workers, and the system handles the rest. See the [Router Guide](../../docs/components/router/router_guide.md#disaggregated-serving) for more details.
+No additional configuration is needed - simply launch both decode and prefill workers, and the system handles the rest. See the [Router Guide](../../docs/pages/components/router/router-guide.md#disaggregated-serving) for more details.
 
 > [!Note]
 > The unified frontend with automatic prefill routing is currently enabled for vLLM and TensorRT-LLM backends. For SGLang (work in progress), you need to launch a separate standalone router as the prefill router targeting the prefill endpoints. See example script: [`examples/backends/sglang/launch/disagg_router.sh`](../../examples/backends/sglang/launch/disagg_router.sh)

components/README.md

@@ -25,9 +25,9 @@ This directory contains the core components that make up the Dynamo inference fr
 
 Dynamo supports multiple inference engines, each with their own deployment configurations and capabilities:
 
-- **[vLLM](/docs/backends/vllm/README.md)** - Full-featured vLLM integration with disaggregated serving, KV-aware routing, SLA-based planning, native KV cache events, and NIXL-based transfer mechanisms
-- **[SGLang](/docs/backends/sglang/README.md)** - SGLang engine integration with ZMQ-based communication, supporting disaggregated serving and KV-aware routing
-- **[TensorRT-LLM](/docs/backends/trtllm/README.md)** - TensorRT-LLM integration with disaggregated serving capabilities and TensorRT acceleration
+- **[vLLM](/docs/pages/backends/vllm/README.md)** - Full-featured vLLM integration with disaggregated serving, KV-aware routing, SLA-based planning, native KV cache events, and NIXL-based transfer mechanisms
+- **[SGLang](/docs/pages/backends/sglang/README.md)** - SGLang engine integration with ZMQ-based communication, supporting disaggregated serving and KV-aware routing
+- **[TensorRT-LLM](/docs/pages/backends/trtllm/README.md)** - TensorRT-LLM integration with disaggregated serving capabilities and TensorRT acceleration
 
 Each engine provides launch and deploy scripts for different deployment patterns in the [examples](../examples/backends/) folder.
 

components/src/dynamo/frontend/README.md

@@ -5,4 +5,4 @@
 
 The API gateway for serving LLM inference requests with OpenAI-compatible HTTP and KServe gRPC endpoints.
 
-See [docs/components/frontend/](../../../../docs/components/frontend/) for documentation.
+See [docs/pages/components/frontend/](../../../../docs/pages/components/frontend/) for documentation.

components/src/dynamo/mocker/README.md

@@ -64,7 +64,7 @@ python -m dynamo.mocker \
 
 The profile results directory should contain `selected_prefill_interpolation/` and `selected_decode_interpolation/` subdirectories with `raw_data.npz` files. This works seamlessly in Kubernetes where profile data is mounted via ConfigMap or PersistentVolume.
 
-To generate profiling data for your own model/hardware configuration, run the profiler (see [SLA-driven profiling documentation](../../../../docs/components/profiler/profiler_guide.md) for details):
+To generate profiling data for your own model/hardware configuration, run the profiler (see [SLA-driven profiling documentation](../../../../docs/pages/components/profiler/profiler-guide.md) for details):
 
 ```bash
 python benchmarks/profiler/profile_sla.py \

components/src/dynamo/planner/README.md

@@ -19,5 +19,5 @@ limitations under the License.
 
 SLA-driven autoscaling controller for Dynamo inference graphs.
 
-- **User docs**: [docs/planner/](/docs/components/planner/) (deployment, configuration, examples)
-- **Design docs**: [docs/design_docs/planner_design.md](/docs/design_docs/planner_design.md) (architecture, algorithms)
+- **User docs**: [docs/planner/](/docs/pages/components/planner/) (deployment, configuration, examples)
+- **Design docs**: [docs/pages/design-docs/planner-design.md](/docs/pages/design-docs/planner-design.md) (architecture, algorithms)

components/src/dynamo/planner/utils/perf_interpolation.py

@@ -29,7 +29,7 @@ logger = logging.getLogger(__name__)
 
 MISSING_PROFILING_DATA_ERROR_MESSAGE = (
     "SLA-Planner requires pre-deployment profiling results to run.\n"
-    "Please follow /docs/components/profiler/profiler_guide.md to run the profiling first,\n"
+    "Please follow /docs/pages/components/profiler/profiler-guide.md to run the profiling first,\n"
     "and make sure the profiling results are present in --profile-results-dir."
 )
 

components/src/dynamo/router/README.md

@@ -3,7 +3,7 @@
 
 # Standalone Router
 
-A backend-agnostic standalone KV-aware router service for Dynamo deployments. For details on how KV-aware routing works, see the [Router Guide](/docs/components/router/router_guide.md).
+A backend-agnostic standalone KV-aware router service for Dynamo deployments. For details on how KV-aware routing works, see the [Router Guide](/docs/pages/components/router/router-guide.md).
 
 ## Overview
 
@@ -29,7 +29,7 @@ python -m dynamo.router \
 - `--endpoint`: Full endpoint path for workers in the format `namespace.component.endpoint` (e.g., `dynamo.prefill.generate`)
 
 **Router Configuration:**
-For detailed descriptions of all KV router configuration options including `--block-size`, `--kv-overlap-score-weight`, `--router-temperature`, `--no-kv-events`, `--router-replica-sync`, `--router-snapshot-threshold`, `--router-reset-states`, and `--no-track-active-blocks`, see the [Router Guide](/docs/components/router/router_guide.md).
+For detailed descriptions of all KV router configuration options including `--block-size`, `--kv-overlap-score-weight`, `--router-temperature`, `--no-kv-events`, `--router-replica-sync`, `--router-snapshot-threshold`, `--router-reset-states`, and `--no-track-active-blocks`, see the [Router Guide](/docs/pages/components/router/router-guide.md).
 
 ## Architecture
 
@@ -43,7 +43,7 @@ Clients query the `find_best_worker` endpoint to determine which worker should p
 ## Example: Manual Disaggregated Serving (Alternative Setup)
 
 > [!Note]
-> **This is an alternative advanced setup.** The recommended approach for disaggregated serving is to use the frontend's automatic prefill routing, which activates when you register workers with `ModelType.Prefill`. See the [Router Guide](/docs/components/router/router_guide.md#disaggregated-serving) for the default setup.
+> **This is an alternative advanced setup.** The recommended approach for disaggregated serving is to use the frontend's automatic prefill routing, which activates when you register workers with `ModelType.Prefill`. See the [Router Guide](/docs/pages/components/router/router-guide.md#disaggregated-serving) for the default setup.
 >
 > Use this manual setup if you need explicit control over prefill routing configuration or want to manage prefill and decode routers separately.
 
@@ -103,7 +103,7 @@ See [`components/src/dynamo/vllm/handlers.py`](../vllm/handlers.py) for a refere
 
 ## See Also
 
-- [Router Guide](/docs/components/router/router_guide.md) - Configuration and tuning for KV-aware routing
-- [Router Design](/docs/design_docs/router_design.md) - Architecture details and event transport modes
+- [Router Guide](/docs/pages/components/router/router-guide.md) - Configuration and tuning for KV-aware routing
+- [Router Design](/docs/pages/design-docs/router-design.md) - Architecture details and event transport modes
 - [Frontend Router](../frontend/README.md) - Main HTTP frontend with integrated routing
 - [Router Benchmarking](/benchmarks/router/README.md) - Performance testing and tuning

components/src/dynamo/trtllm/engines/diffusion_engine.py

@@ -13,7 +13,7 @@ Requirements:
     - visual_gen: Part of TensorRT-LLM, located at tensorrt_llm/visual_gen/.
       Currently on the feat/visual_gen branch (not yet merged to main).
       See: https://github.com/NVIDIA/TensorRT-LLM/tree/feat/visual_gen/tensorrt_llm/visual_gen
-    - See docs/backends/trtllm/README.md for setup instructions.
+    - See docs/pages/backends/trtllm/README.md for setup instructions.
 
 Note on imports:
     visual_gen is imported lazily in initialize() because:

components/src/dynamo/trtllm/workers/video_diffusion_worker.py

@@ -85,7 +85,7 @@ async def init_video_diffusion_worker(
         raise RuntimeError(
             "ModelType.Videos not available in dynamo-runtime. "
             "Video diffusion requires a compatible dynamo-runtime version. "
-            "See docs/backends/trtllm/README.md for setup instructions."
+            "See docs/pages/backends/trtllm/README.md for setup instructions."
         )
     model_type = ModelType.Videos
 

deploy/README.md

-../docs/kubernetes/README.md
\ No newline at end of file