Stop using title frontmatter and fix doc that can only be reached by search (#20623)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

docs/design/arch_overview.md

----
-title: Architecture Overview
----
+# Architecture Overview
 
 This document provides an overview of the vLLM architecture.
 

docs/design/automatic_prefix_caching.md

----
-title: Automatic Prefix Caching
----
+# Automatic Prefix Caching
 
 The core idea of [PagedAttention](https://blog.vllm.ai/2023/06/20/vllm.html) is to partition the KV cache of each request into KV Blocks. Each block contains the attention keys and values for a fixed number of tokens. The PagedAttention algorithm allows these blocks to be stored in non-contiguous physical memory so that we can eliminate memory fragmentation by allocating the memory on demand.
 

docs/design/huggingface_integration.md

----
-title: Integration with HuggingFace
----
+# Integration with HuggingFace
 
 This document describes how vLLM integrates with HuggingFace libraries. We will explain step by step what happens under the hood when we run `vllm serve`.
 

docs/design/kernel/paged_attention.md

----
-title: vLLM Paged Attention
----
+# vLLM Paged Attention
 
 Currently, vLLM utilizes its own implementation of a multi-head query
 attention kernel (`csrc/attention/attention_kernels.cu`).

docs/design/mm_processing.md

----
-title: Multi-Modal Data Processing
----
+# Multi-Modal Data Processing
 
 To enable various optimizations in vLLM such as [chunked prefill][chunked-prefill] and [prefix caching](../features/automatic_prefix_caching.md), we use [BaseMultiModalProcessor][vllm.multimodal.processing.BaseMultiModalProcessor] to provide the correspondence between placeholder feature tokens (e.g. `<image>`) and multi-modal inputs (e.g. the raw input image) based on the outputs of HF processor.
 

docs/design/plugin_system.md

----
-title: vLLM's Plugin System
----
+# vLLM's Plugin System
 
 The community frequently requests the ability to extend vLLM with custom features. To facilitate this, vLLM includes a plugin system that allows users to add custom features without modifying the vLLM codebase. This document explains how plugins work in vLLM and how to create a plugin for vLLM.
 

docs/features/automatic_prefix_caching.md

----
-title: Automatic Prefix Caching
----
+# Automatic Prefix Caching
 
 ## Introduction
 

docs/features/compatibility_matrix.md

----
-title: Compatibility Matrix
----
+# Compatibility Matrix
 
 The tables below show mutually exclusive features and the support on some hardware.
 

docs/features/disagg_prefill.md

----
-title: Disaggregated Prefilling (experimental)
----
+# Disaggregated Prefilling (experimental)
 
 This page introduces you the disaggregated prefilling feature in vLLM.
 

docs/features/lora.md

----
-title: LoRA Adapters
----
+# LoRA Adapters
 
 This document shows you how to use [LoRA adapters](https://arxiv.org/abs/2106.09685) with vLLM on top of a base model.
 

docs/features/multimodal_inputs.md

----
-title: Multimodal Inputs
----
+# Multimodal Inputs
 
 This page teaches you how to pass multi-modal inputs to [multi-modal models][supported-mm-models] in vLLM.
 

docs/features/quantization/README.md

----
-title: Quantization
----
+# Quantization
 
 Quantization trades off model precision for smaller memory footprint, allowing large models to be run on a wider range of devices.
 

docs/features/quantization/auto_awq.md

----
-title: AutoAWQ
----
+# AutoAWQ
 
 To create a new 4-bit quantized model, you can leverage [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
 Quantization reduces the model's precision from BF16/FP16 to INT4 which effectively reduces the total model memory footprint.

docs/features/quantization/bitblas.md

----
-title: BitBLAS
----
+# BitBLAS
 
 vLLM now supports [BitBLAS](https://github.com/microsoft/BitBLAS) for more efficient and flexible model inference. Compared to other quantization frameworks, BitBLAS provides more precision combinations.
 

docs/features/quantization/bnb.md

----
-title: BitsAndBytes
----
+# BitsAndBytes
 
 vLLM now supports [BitsAndBytes](https://github.com/TimDettmers/bitsandbytes) for more efficient model inference.
 BitsAndBytes quantizes models to reduce memory usage and enhance performance without significantly sacrificing accuracy.

docs/features/quantization/fp8.md

----
-title: FP8 W8A8
----
+# FP8 W8A8
 
 vLLM supports FP8 (8-bit floating point) weight and activation quantization using hardware acceleration on GPUs such as Nvidia H100 and AMD MI300x.
 Currently, only Hopper and Ada Lovelace GPUs are officially supported for W8A8.

docs/features/quantization/gguf.md

----
-title: GGUF
----
+# GGUF
 
 !!! warning
     Please note that GGUF support in vLLM is highly experimental and under-optimized at the moment, it might be incompatible with other features. Currently, you can use GGUF as a way to reduce memory footprint. If you encounter any issues, please report them to the vLLM team.

docs/features/quantization/gptqmodel.md

----
-title: GPTQModel
----
+# GPTQModel
 
 To create a new 4-bit or 8-bit GPTQ quantized model, you can leverage [GPTQModel](https://github.com/ModelCloud/GPTQModel) from ModelCloud.AI.
 

docs/features/quantization/int4.md

----
-title: INT4 W4A16
----
+# INT4 W4A16
 
 vLLM supports quantizing weights to INT4 for memory savings and inference acceleration. This quantization method is particularly useful for reducing model size and maintaining low latency in workloads with low queries per second (QPS).
 

docs/features/quantization/int8.md

----
-title: INT8 W8A8
----
+# INT8 W8A8
 
 vLLM supports quantizing weights and activations to INT8 for memory savings and inference acceleration.
 This quantization method is particularly useful for reducing model size while maintaining good performance.