Unverified Commit 2c3066bd authored by dagil-nvidia's avatar dagil-nvidia Committed by GitHub
Browse files

docs: full migration of docs/ to fern format in fern/ (#6050)


Signed-off-by: default avatarDan Gil <dagil@nvidia.com>
Co-authored-by: default avatarCursor <cursoragent@cursor.com>
parent d59b9d72
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
---
{/* 2-3 sentence overview of what this component does and its role in Dynamo */}
## Feature Matrix
| Feature | Status |
|---------|--------|
| Feature 1 | ✅ Supported |
| Feature 2 | 🚧 Experimental |
| Feature 3 | ❌ Not Supported |
## Quick Start
### Prerequisites
- {/* List prerequisites */}
### Usage
```bash
# Add minimal usage example from existing docs
# Example pattern (from Router):
# python -m dynamo.frontend --router-mode kv --http-port 8000
```
### Kubernetes
```yaml
# Add DGDR example - use apiVersion: nvidia.com/v1alpha1
# Example pattern (from Router):
# apiVersion: nvidia.com/v1alpha1
# kind: DynamoGraphDeployment
# metadata:
# name: <component>-deployment
# spec:
# services:
# ...
```
{/* EXAMPLE: Filled-in Quick Start for Router would look like:
### Prerequisites
- Dynamo platform installed
- At least one backend worker running
### Usage
```bash
python -m dynamo.frontend --router-mode kv --http-port 8000
```
### Kubernetes
```yaml
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
name: router-example
spec:
graphs:
- name: frontend
replicas: 1
``` */}
## Configuration
| Parameter | Default | Description |
|-----------|---------|-------------|
| {/* param */} | {/* default */} | {/* description */} |
## Next Steps
| Document | Path | Description |
|----------|------|-------------|
| `<Component> Guide` | `<component>_guide.md` | Deployment and configuration |
| `<Component> Examples` | `<component>_examples.md` | Usage examples |
| `<Component> Design` | `/docs/design_docs/`\<component>`_design.md` | Architecture |
{/* Convert table rows to markdown links */}
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
---
Using `<Feature>` with the `<Backend>` backend.
## Prerequisites
- `<Backend>` installed with `<feature>` support
- {/* Other requirements */}
## Configuration
### CLI Arguments
| Argument | Default | Description |
|----------|---------|-------------|
| {/* arg */} | {/* default */} | {/* description */} |
### Environment Variables
| Variable | Default | Description |
|----------|---------|-------------|
| {/* var */} | {/* default */} | {/* description */} |
## Examples
### Basic Usage
```python
# Add example from existing docs
```
### Kubernetes Deployment
```yaml
# Add DGDR example from existing docs
```
## Limitations
- {/* Backend-specific limitations */}
## Troubleshooting
| Issue | Solution |
|-------|----------|
| {/* issue */} | {/* solution */} |
## See Also
| Document | Path |
|----------|------|
| `<Feature> Overview` | `./README.md` |
| `<Backend> Guide` | `/docs/backends/`\<backend>`/README.md` |
{/* Convert to links: [Multimodal Overview](./README.md) */}
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
---
{/* 2-3 sentence overview of this cross-cutting feature */}
## Backend Support
{/* Copy actual backend support from existing feature docs */}
{/* Example pattern (from Multimodal index.md): */}
| Backend | Status | Notes |
|---------|--------|-------|
| vLLM | ✅ | Full support |
| SGLang | ✅ | |
| TensorRT-LLM | 🚧 | Limited support |
See the Feature Matrix for full compatibility.
## Overview
{/* How this feature works across backends */}
## Quick Start
{/* Add minimal example from existing feature docs */}
## Backend-Specific Guides
| Backend | Guide |
|---------|-------|
| vLLM | `<feature>_vllm.md` |
| SGLang | `<feature>_sglang.md` |
| TensorRT-LLM | `<feature>_trtllm.md` |
{/* Convert table rows to markdown links */}
## See Also
- {/* Related features */}
- {/* Related components */}
......@@ -3,8 +3,9 @@
# SPDX-License-Identifier: Apache-2.0
---
# KVBM Further Reading
{/* One-sentence description */}
- [vLLM](https://docs.vllm.ai/en/latest/features/automatic_prefix_caching.html)
- [SGLang](https://github.com/sgl-project/sglang/tree/main/benchmark/hicache)
- [EMOGI](https://arxiv.org/abs/2006.06890)
\ No newline at end of file
See `docs/components/`\<component>`/` for full documentation.
{/* When using this template, replace with actual link to component docs.
For backends, use: docs/backends/`<backend>`/ */}
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
---
{/* 2-3 sentence overview of this infrastructure topic. */}
## Quick Start
{/* Minimal steps to get started */}
## Guides
| Guide | Path |
|-------|------|
| Guide 1 | `<subtopic1>.md` |
| Guide 2 | `<subtopic2>.md` |
## Reference
{/* Links to reference material */}
## See Also
| Topic | Path |
|-------|------|
| Related topic 1 | `../related/` |
| Related topic 2 | `../other/` |
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
---
{/* 2-3 sentence overview of this external integration */}
## Version Compatibility
| Dynamo | `<Integration>` | Notes |
|--------|---------------|-------|
| 0.9.x | 1.2.x | Recommended |
| 0.8.x | 1.1.x | |
## Backend Support
| Backend | Status | Notes |
|---------|--------|-------|
| vLLM | ✅ | |
| SGLang | 🚧 | |
| TensorRT-LLM | ❌ | |
## Quick Start
```bash
# Add installation and usage from existing integration docs
# Example pattern (LMCache):
# python -m dynamo.vllm --model <model> --connector lmcache
```
## Configuration
| Parameter | Default | Description |
|-----------|---------|-------------|
| {/* param */} | {/* default */} | {/* description */} |
## Guides
| Document | Path | Description |
|----------|------|-------------|
| `<Integration> Setup` | `<integration>_setup.md` | Installation and configuration |
| `<Integration> with vLLM` | `<integration>_vllm.md` | vLLM-specific usage |
{/* Convert table rows to markdown links */}
## External Resources
- [`<Integration>` Documentation](https://...)
- [`<Integration>` GitHub](https://github.com/...)
......@@ -13,8 +13,8 @@
# See the License for the specific language governing permissions and
# limitations under the License.
# Navigation structure for Latest version
# Matching https://docs.nvidia.com/dynamo/latest/
# Navigation structure matching https://docs.nvidia.com/dynamo/dev/
# Rebuilt to exactly replicate the rendered Sphinx sidebar
navigation:
# ==================== Getting Started ====================
......@@ -22,8 +22,6 @@ navigation:
contents:
- page: Quickstart
path: ../pages/getting-started/quickstart.md
- page: Installation
path: ../pages/getting-started/installation.md
- page: Support Matrix
path: ../pages/reference/support-matrix.md
- page: Feature Matrix
......@@ -37,39 +35,37 @@ navigation:
- section: Kubernetes Deployment
contents:
- section: Deployment Guide
path: ../pages/kubernetes/README.md
contents:
- page: Kubernetes Quickstart
path: ../pages/kubernetes/README.md
- page: Detailed Installation Guide
path: ../pages/kubernetes/installation-guide.md
- page: Dynamo Operator
path: ../pages/kubernetes/dynamo-operator.md
- page: Minikube Setup
path: ../pages/kubernetes/deployment/minikube-setup.md
- page: Managing Models with DynamoModel
path: ../pages/kubernetes/deployment/dynamomodel-guide.md
- page: Service Discovery
path: ../pages/kubernetes/service-discovery.md
- page: Webhooks
path: ../pages/kubernetes/webhooks.md
- page: Minikube Setup
path: ../pages/kubernetes/deployment/minikube.md
- page: Managing Models with DynamoModel
path: ../pages/kubernetes/deployment/dynamomodel-guide.md
- page: Autoscaling
path: ../pages/kubernetes/autoscaling.md
- section: Checkpointing (ChReK)
contents:
- page: Overview
- section: Checkpointing
path: ../pages/kubernetes/chrek/README.md
- page: Integration with Dynamo
path: ../pages/kubernetes/chrek/dynamo.md
- page: Standalone Usage
path: ../pages/kubernetes/chrek/standalone.md
contents:
- page: Integration with Dynamo
path: ../pages/kubernetes/chrek/dynamo.md
- page: Standalone Usage
path: ../pages/kubernetes/chrek/standalone.md
- section: Observability (K8s)
contents:
- page: Metrics
path: ../pages/kubernetes/observability/metrics.md
- page: Operator Metrics
path: ../pages/kubernetes/observability/operator-metrics.md
- page: Logging
path: ../pages/kubernetes/observability/logging.md
- page: Operator Metrics
path: ../pages/kubernetes/observability/operator-metrics.md
- section: Multinode
contents:
- page: Multinode Deployments
......@@ -80,22 +76,30 @@ navigation:
# ==================== User Guides ====================
- section: User Guides
contents:
- page: Tool Calling
path: ../pages/agents/tool-calling.md
- page: Multimodality Support
path: ../pages/multimodal/index.md
- page: Finding Best Initial Configs
path: ../pages/performance/aiconfigurator.md
- page: KV Cache Aware Routing
path: ../pages/components/router/router-guide.md
- page: Disaggregated Serving Guide
path: ../pages/features/disaggregated-serving/README.md
- page: KV Cache Offloading
path: ../pages/components/kvbm/kvbm-guide.md
- page: Dynamo Benchmarking Guide
path: ../pages/benchmarks/benchmarking.md
- page: Tuning Disaggregated Performance
path: ../pages/performance/tuning.md
- page: Writing Python Workers in Dynamo
path: ../pages/development/backend-guide.md
- section: Multimodality Support
path: ../pages/features/multimodal/README.md
contents:
- page: vLLM Multimodal
path: ../pages/features/multimodal/multimodal-vllm.md
- page: TensorRT-LLM Multimodal
path: ../pages/features/multimodal/multimodal-trtllm.md
- page: SGLang Multimodal
path: ../pages/features/multimodal/multimodal-sglang.md
- page: Tool Calling
path: ../pages/agents/tool-calling.md
- page: LoRA Adapters
path: ../pages/features/lora/README.md
- section: Observability (Local)
path: ../pages/observability/README.md
contents:
- page: Overview
path: ../pages/observability/README.md
- page: Prometheus + Grafana Setup
path: ../pages/observability/prometheus-grafana.md
- page: Metrics
......@@ -109,9 +113,8 @@ navigation:
- page: Logging
path: ../pages/observability/logging.md
- section: Fault Tolerance
path: ../pages/fault-tolerance/README.md
contents:
- page: Overview
path: ../pages/fault-tolerance/README.md
- page: Request Migration
path: ../pages/fault-tolerance/request-migration.md
- page: Request Cancellation
......@@ -122,8 +125,8 @@ navigation:
path: ../pages/fault-tolerance/request-rejection.md
- page: Testing
path: ../pages/fault-tolerance/testing.md
- page: Glossary
path: ../pages/reference/glossary.md
- page: Writing Python Workers in Dynamo
path: ../pages/development/backend-guide.md
# ==================== Components ====================
- section: Components
......@@ -136,44 +139,49 @@ navigation:
path: ../pages/backends/sglang/README.md
- page: TensorRT-LLM
path: ../pages/backends/trtllm/README.md
- section: Frontends
- section: Frontend
path: ../pages/components/frontend/README.md
contents:
- page: Frontend Guide
path: ../pages/components/frontend/frontend-guide.md
- section: Router
path: ../pages/components/router/README.md
contents:
- page: KServe
path: ../pages/frontends/kserve.md
- page: Router
path: ../pages/router/README.md
- page: Router Guide
path: ../pages/components/router/router-guide.md
- page: Router Examples
path: ../pages/components/router/router-examples.md
- section: Planner
path: ../pages/components/planner/README.md
contents:
- page: Planner Guide
path: ../pages/components/planner/planner-guide.md
- page: Planner Examples
path: ../pages/components/planner/planner-examples.md
- section: Profiler
path: ../pages/components/profiler/README.md
contents:
- page: Overview
path: ../pages/planner/planner-intro.md
- page: SLA Planner Quick Start
path: ../pages/planner/sla-planner-quickstart.md
- page: SLA-Driven Profiling
path: ../pages/benchmarks/sla-driven-profiling.md
- page: SLA-based Planner
path: ../pages/planner/sla-planner.md
- page: Profiler Guide
path: ../pages/components/profiler/profiler-guide.md
- page: Profiler Examples
path: ../pages/components/profiler/profiler-examples.md
- section: KVBM
path: ../pages/components/kvbm/README.md
contents:
- page: Overview
path: ../pages/kvbm/kvbm-intro.md
- page: Motivation
path: ../pages/kvbm/kvbm-motivation.md
- page: Architecture
path: ../pages/kvbm/kvbm-architecture.md
- page: Components
path: ../pages/kvbm/kvbm-components.md
- page: Design Deep Dive
path: ../pages/kvbm/kvbm-design-deepdive.md
- page: Integrations
path: ../pages/kvbm/kvbm-integrations.md
- page: KVBM in vLLM
path: ../pages/kvbm/vllm-setup.md
- page: KVBM in TRTLLM
path: ../pages/kvbm/trtllm-setup.md
- page: LMCache Integration
path: ../pages/backends/vllm/LMCache-Integration.md
- page: Further Reading
path: ../pages/kvbm/kvbm-reading.md
- page: KVBM Guide
path: ../pages/components/kvbm/kvbm-guide.md
# ==================== Integrations ====================
- section: Integrations
contents:
- page: LMCache
path: ../pages/integrations/lmcache-integration.md
- page: SGLang HiCache
path: ../pages/integrations/sglang-hicache.md
- page: FlexKV
path: ../pages/integrations/flexkv-integration.md
- page: KV Events for Custom Engines
path: ../pages/integrations/kv-events-custom-engines.md
# ==================== Design Docs ====================
- section: Design Docs
......@@ -187,132 +195,147 @@ navigation:
- page: Distributed Runtime
path: ../pages/design-docs/distributed-runtime.md
- page: Request Plane
path: ../pages/guides/request-plane.md
path: ../pages/design-docs/request-plane.md
- page: Event Plane
path: ../pages/design-docs/event-plane.md
- page: Router Design
path: ../pages/design-docs/router-design.md
- page: KVBM Design
path: ../pages/design-docs/kvbm-design.md
- page: Planner Design
path: ../pages/design-docs/planner-design.md
# ==================== Additional Resources ====================
# Hidden section - these pages are accessible via direct URL but not shown in navigation
# ==================== Hidden Pages ====================
# Pages accessible via direct URL but not shown in main navigation.
# Matches Sphinx hidden_toctree.rst -- pages linked from within content
# but not in the sidebar.
- section: Additional Resources
hidden: true
contents:
- section: Advanced Kubernetes
# -- Development --
- page: Runtime Guide
path: ../pages/development/runtime-guide.md
- page: Jail Stream
path: ../pages/development/jail-stream.md
# -- API Reference --
- section: NIXL Connect API
path: ../pages/api/nixl-connect/README.md
contents:
- page: Create Deployment
path: ../pages/kubernetes/deployment/create-deployment.md
- page: Autoscaling
path: ../pages/kubernetes/autoscaling.md
- page: Service Discovery
path: ../pages/kubernetes/service-discovery.md
- page: Model Caching with Fluid
path: ../pages/kubernetes/model-caching-with-fluid.md
- page: FluxCD
path: ../pages/kubernetes/fluxcd.md
- page: Webhooks
path: ../pages/kubernetes/webhooks.md
- page: API Reference
path: ../pages/kubernetes/api-reference.md
- section: Multimodal Details
- page: Connector
path: ../pages/api/nixl-connect/connector.md
- page: Device
path: ../pages/api/nixl-connect/device.md
- page: Device Kind
path: ../pages/api/nixl-connect/device-kind.md
- page: Descriptor
path: ../pages/api/nixl-connect/descriptor.md
- page: Read Operation
path: ../pages/api/nixl-connect/read-operation.md
- page: Write Operation
path: ../pages/api/nixl-connect/write-operation.md
- page: Readable Operation
path: ../pages/api/nixl-connect/readable-operation.md
- page: Writable Operation
path: ../pages/api/nixl-connect/writable-operation.md
- page: Operation Status
path: ../pages/api/nixl-connect/operation-status.md
- page: RDMA Metadata
path: ../pages/api/nixl-connect/rdma-metadata.md
# -- Kubernetes (hidden sub-pages) --
- page: API Reference (K8s)
path: ../pages/kubernetes/api-reference.md
- page: Creating Deployments
path: ../pages/kubernetes/deployment/create-deployment.md
- page: FluxCD
path: ../pages/kubernetes/fluxcd.md
- page: Model Caching with Fluid
path: ../pages/kubernetes/model-caching-with-fluid.md
# -- Reference --
- page: CLI Reference
path: ../pages/reference/cli.md
- page: Glossary
path: ../pages/reference/glossary.md
- page: Tuning Disaggregated Performance
path: ../pages/performance/tuning.md
# -- Backend detail pages --
- section: vLLM Details
contents:
- page: vLLM
path: ../pages/multimodal/vllm.md
- page: SGLang
path: ../pages/multimodal/sglang.md
- page: TensorRT-LLM
path: ../pages/multimodal/trtllm.md
- section: Router Details
- page: DeepSeek-R1
path: ../pages/backends/vllm/deepseek-r1.md
- page: GPT-OSS
path: ../pages/backends/vllm/gpt-oss.md
- page: Multi-Node
path: ../pages/backends/vllm/multi-node.md
- page: Prometheus
path: ../pages/backends/vllm/prometheus.md
- page: Prompt Embeddings
path: ../pages/backends/vllm/prompt-embeddings.md
- section: SGLang Details
contents:
- page: KV Cache Routing
path: ../pages/router/kv-cache-routing.md
- section: Benchmarks
- page: Expert Distribution (EPLB)
path: ../pages/backends/sglang/expert-distribution-eplb.md
- page: GPT-OSS
path: ../pages/backends/sglang/gpt-oss.md
- page: Diffusion LM
path: ../pages/backends/sglang/diffusion-lm.md
- page: Profiling
path: ../pages/backends/sglang/profiling.md
- page: Disaggregation
path: ../pages/backends/sglang/sglang-disaggregation.md
- page: Prometheus
path: ../pages/backends/sglang/prometheus.md
- section: TensorRT-LLM Details
contents:
- page: KV Router A/B Testing
path: ../pages/benchmarks/kv-router-ab-testing.md
- section: Frontends
- page: Multinode Examples
path: ../pages/backends/trtllm/multinode/multinode-examples.md
- page: Llama4 + Eagle
path: ../pages/backends/trtllm/llama4-plus-eagle.md
- page: KV Cache Transfer
path: ../pages/backends/trtllm/kv-cache-transfer.md
- page: Gemma3 Sliding Window
path: ../pages/backends/trtllm/gemma3-sliding-window-attention.md
- page: GPT-OSS
path: ../pages/backends/trtllm/gpt-oss.md
- page: Prometheus
path: ../pages/backends/trtllm/prometheus.md
# -- Features (hidden sub-pages) --
- section: Speculative Decoding
path: ../pages/features/speculative-decoding/README.md
contents:
- page: KServe
path: ../pages/frontends/kserve.md
- section: Development
- page: Speculative Decoding with vLLM
path: ../pages/features/speculative-decoding/speculative-decoding-vllm.md
# -- Benchmarks --
- page: KV Router A/B Testing
path: ../pages/benchmarks/kv-router-ab-testing.md
# -- Mocker --
- page: Mocker
path: ../pages/mocker/mocker.md
# -- Docs README --
- page: Building Documentation
path: ../pages/README.md
# -- Templates --
- section: Templates
path: ../pages/templates/README.md
contents:
- page: Backend Guide
path: ../pages/development/backend-guide.md
- section: Guides
contents:
- page: Request Plane
path: ../pages/guides/request-plane.md
- page: Jail Stream
path: ../pages/guides/jail-stream-readme.md
- page: Load Planner
path: ../pages/planner/load-planner.md
- page: CLI Reference
path: ../pages/reference/cli.md
- section: API Reference
contents:
- section: NIXL Connect
contents:
- page: Overview
path: ../pages/api/nixl-connect/README.md
- page: Connector
path: ../pages/api/nixl-connect/connector.md
- page: Device
path: ../pages/api/nixl-connect/device.md
- page: Device Kind
path: ../pages/api/nixl-connect/device-kind.md
- page: Descriptor
path: ../pages/api/nixl-connect/descriptor.md
- page: Read Operation
path: ../pages/api/nixl-connect/read-operation.md
- page: Write Operation
path: ../pages/api/nixl-connect/write-operation.md
- page: Readable Operation
path: ../pages/api/nixl-connect/readable-operation.md
- page: Writable Operation
path: ../pages/api/nixl-connect/writable-operation.md
- page: Operation Status
path: ../pages/api/nixl-connect/operation-status.md
- page: RDMA Metadata
path: ../pages/api/nixl-connect/rdma-metadata.md
- section: Backend Details
contents:
- section: vLLM
contents:
- page: DeepSeek-R1
path: ../pages/backends/vllm/deepseek-r1.md
- page: GPT-OSS
path: ../pages/backends/vllm/gpt-oss.md
- page: Multi-Node
path: ../pages/backends/vllm/multi-node.md
- page: Speculative Decoding
path: ../pages/backends/vllm/speculative-decoding.md
- page: Prompt Embeddings
path: ../pages/backends/vllm/prompt-embeddings.md
- page: Prometheus
path: ../pages/backends/vllm/prometheus.md
- section: SGLang
contents:
- page: GPT-OSS
path: ../pages/backends/sglang/gpt-oss.md
- page: Disaggregation
path: ../pages/backends/sglang/sglang-disaggregation.md
- page: Expert Distribution (EPLB)
path: ../pages/backends/sglang/expert-distribution-eplb.md
- page: HiCache Example
path: ../pages/backends/sglang/sgl-hicache-example.md
- page: Profiling
path: ../pages/backends/sglang/profiling.md
- page: Prometheus
path: ../pages/backends/sglang/prometheus.md
- section: TensorRT-LLM
contents:
- page: GPT-OSS
path: ../pages/backends/trtllm/gpt-oss.md
- page: KV Cache Transfer
path: ../pages/backends/trtllm/kv-cache-transfer.md
- page: Gemma3 Sliding Window
path: ../pages/backends/trtllm/gemma3-sliding-window-attention.md
- page: Llama4 + Eagle
path: ../pages/backends/trtllm/llama4-plus-eagle.md
- page: Multinode Examples
path: ../pages/backends/trtllm/multinode/multinode-examples.md
- page: Prometheus
path: ../pages/backends/trtllm/prometheus.md
path: ../pages/templates/backend-guide.md
- page: Backend README
path: ../pages/templates/backend-readme.md
- page: Component Design
path: ../pages/templates/component-design.md
- page: Component Examples
path: ../pages/templates/component-examples.md
- page: Component Guide
path: ../pages/templates/component-guide.md
- page: Component README
path: ../pages/templates/component-readme.md
- page: Feature Backend
path: ../pages/templates/feature-backend.md
- page: Feature README
path: ../pages/templates/feature-readme.md
- page: In-Code README
path: ../pages/templates/incode-readme.md
- page: Infrastructure README
path: ../pages/templates/infrastructure-readme.md
- page: Integration README
path: ../pages/templates/integration-readme.md
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment