Unverified Commit dd6c3995 authored by dagil-nvidia's avatar dagil-nvidia Committed by GitHub
Browse files

docs: add frontmatter title to all docs pages (#6254)


Signed-off-by: default avatarDan Gil <dagil@nvidia.com>
Co-authored-by: default avatarCursor <cursoragent@cursor.com>
parent bbe82f18
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Jail Stream
---
# JailedStream Implementation
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Runtime Guide
---
# Dynamo Runtime
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Fault Tolerance
subtitle: Handle failures gracefully with request migration, cancellation, and graceful shutdown
---
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Graceful Shutdown
---
# Graceful Shutdown
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Request Cancellation
---
This document describes how Dynamo implements request cancellation to cancel in-flight requests between Dynamo workers. Request cancellation allows in-flight requests to terminate early, saving computational resources that would otherwise be spent on responses that are no longer needed.
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Request Migration
---
This document describes how Dynamo implements request migration to handle worker failures gracefully during LLM text generation. Request migration allows in-progress requests to continue on different workers when the original worker becomes unavailable, providing fault tolerance and improved user experience.
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Request Rejection
---
# Request Rejection (Load Shedding)
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Testing
---
# Fault Tolerance Testing
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Disaggregated Serving
subtitle: Find optimal prefill/decode configuration for disaggregated serving deployments
---
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: LoRA Adapters
subtitle: Serve fine-tuned LoRA adapters with dynamic loading and routing in Dynamo
---
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Multimodality Support
subtitle: Deploy multimodal models with image, video, and audio support in Dynamo
---
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: SGLang Multimodal
---
# SGLang Multimodal
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: TensorRT-LLM Multimodal
---
# TensorRT-LLM Multimodal
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: vLLM Multimodal
---
# vLLM Multimodal
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Speculative Decoding
---
# Speculative Decoding
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Speculative Decoding with vLLM
---
# Speculative Decoding with vLLM
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Examples
---
The examples below assume you build the latest image yourself from source. If using a prebuilt image, follow the examples from the corresponding branch.
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: Quickstart
---
This guide covers running Dynamo **using the CLI on your local machine or VM**.
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: FlexKV
---
# FlexKV Integration in Dynamo
......
---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: KV Events for Custom Engines
---
# KV Event Publishing for Custom Engines
......
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