docs: update document

Author: future-xy

docs/api/cli.md

@@ -24,7 +24,7 @@ pip install serverless-llm
 
 Before using the `sllm-cli` commands, you need to start the ServerlessLLM cluster. Follow the guides below to set up your cluster:
 
-- [Single Machine Deployment](../stable/gettting_started.md)
+- [Single Machine Deployment](../stable/getting_started.md)
 - [Single Machine Deployment (From Scratch)](../stable/deployment/single_machine.md)
 - [Multi-Machine Deployment](../stable/deployment/multi_machine.md)
 - [SLURM Cluster Deployment](../stable/deployment/slurm_cluster.md)

docs/stable/deployment/single_machine.md

@@ -7,7 +7,7 @@ sidebar_position: 1
 This guide provides instructions for setting up ServerlessLLM from scratch on a single machine. This 'from scratch' approach means you will manually initialize and manage the Ray cluster components. It involves using multiple terminal sessions, each configured with a distinct Conda environment, to run the head and worker processes on the same physical machine, effectively simulating a multi-node deployment locally.
 
 :::note
-We strongly recommend using Docker (Compose) as detailed in the [Docker Compose guide](../gettting_started.md). Docker provides a smoother and generally easier setup process. Follow this guide only if Docker is not a suitable option for your environment.
+We strongly recommend using Docker (Compose) as detailed in the [Docker Compose guide](../getting_started.md). Docker provides a smoother and generally easier setup process. Follow this guide only if Docker is not a suitable option for your environment.
 :::
 
 ## Installation

docs/stable/deployment/slurm_cluster.md

@@ -4,7 +4,7 @@ sidebar_position: 3
 
 # SLURM cluster
 
-This guide will help you get started with running ServerlessLLM on SLURM cluster. It provides two deployment methods, based on `sbatch` and `srun`. If you are in development, we recommend using `srun`, as it is easier to debug than `sbatch`, and if you are in production mode, `sbatch` is recommended. Please make sure you have installed the ServerlessLLM following the [installation guide](./installation.md) on all machines.
+This guide will help you get started with running ServerlessLLM on SLURM cluster. It provides two deployment methods, based on `sbatch` and `srun`. If you are in development, we recommend using `srun`, as it is easier to debug than `sbatch`, and if you are in production mode, `sbatch` is recommended. Please make sure you have installed the ServerlessLLM following the [installation guide](./single_machine.md#installation) on all machines.
 
 ## Pre-requisites
 Before you begin, make sure you have checked the following:

docs/stable/features/live_migration.md

@@ -11,7 +11,7 @@ This example illustrates the live migration of inference instances in a Serverle
 
 ## Prerequisites
 
-To run this example, we will use Docker Compose to set up a ServerlessLLM cluster. Before proceeding, please ensure you have read the [Docker Quickstart Guide](../getting_started/docker_quickstart.md).
+To run this example, we will use Docker Compose to set up a ServerlessLLM cluster. Before proceeding, please ensure you have read the [Quickstart Guide](../getting_started.md).
 
 **Requirements:**
 

docs/stable/features/peft_lora_serving.md

@@ -5,7 +5,7 @@ sidebar_position: 2
 
 ## Pre-requisites
 
-To run this example, we will use Docker Compose to set up a ServerlessLLM cluster. Before proceeding, please ensure you have read the [Docker Quickstart Guide](../getting_started/docker_quickstart.md).
+To run this example, we will use Docker Compose to set up a ServerlessLLM cluster. Before proceeding, please ensure you have read the [Quickstart Guide](../getting_started.md).
 
 We will use the following example base model & LoRA adapter
 - Base model: `facebook/opt-125m`

docs/stable/features/storage_aware_scheduling.md

@@ -6,7 +6,7 @@ sidebar_position: 0
 
 ## Pre-requisites
 
-We will use Docker Compose to run a ServerlessLLM cluster in this example. Therefore, please make sure you have read the [Docker Quickstart Guide](../getting_started/docker_quickstart.md) before proceeding.
+We will use Docker Compose to run a ServerlessLLM cluster in this example. Therefore, please make sure you have read the [Quickstart Guide](../getting_started.md) before proceeding.
 
 ## Usage
 

docs/stable/gettting_started.md

@@ -110,21 +110,31 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## Usage with vLLM
 
-:::tip
-To use ServerlessLLM as the load format for vLLM, you need to apply our patch `sllm_store/vllm_patch/sllm_load.patch` to the installed vLLM library. Therefore, please ensure you have applied our `vLLM Patch` as instructed in [installation guide](../getting_started/installation.md).
+ServerlessLLM integrates with vLLM to provide fast model loading capabilities. Follow these steps to set up and use ServerlessLLM with vLLM.
 
-You may check the patch status by running the following command:
-``` bash
-./sllm_store/vllm_patch/check_patch.sh
-```
-If the patch is not applied, you can apply it by running the following command:
-```bash
-./sllm_store/vllm_patch/patch.sh
-```
-To remove the applied patch, you can run the following command:
-```bash
-./sllm_store/vllm_patch/remove_patch.sh
-```
+### Prerequisites
+
+Before using ServerlessLLM with vLLM, you need to apply a compatibility patch to your vLLM installation. This patch has been tested with vLLM version `0.6.6`.
+
+### Apply the vLLM Patch
+
+1. **Check patch status** (optional):
+   ```bash
+   ./sllm_store/vllm_patch/check_patch.sh
+   ```
+
+2. **Apply the patch**:
+   ```bash
+   ./sllm_store/vllm_patch/patch.sh
+   ```
+
+3. **Remove the patch** (if needed):
+   ```bash
+   ./sllm_store/vllm_patch/remove_patch.sh
+   ```
+
+:::note
+The patch file is located at `sllm_store/vllm_patch/sllm_load.patch` in the ServerlessLLM repository.
 :::