docs: add self hosting docs

website/docs/getting-started.md

@@ -1,11 +1,6 @@
-# Client
+# Getting Started
 
-We offer multiple methods to connect to Tabby Server, including editor extensions and OpenAPI.
-
-## Editor Extensions
+Install Tabby in your code editors, if your favorite editor is not supported yet, consider filing an [Feature Request](https://github.com/TabbyML/tabby/issues/new?assignees=&labels=enhancement&projects=&template=feature_request.md&title=).
 
 * [VSCode Extension](https://github.com/TabbyML/tabby/tree/main/clients/vscode) – Install from the [marketplace](https://marketplace.visualstudio.com/items?itemName=TabbyML.vscode-tabby), or [open-vsx.org](https://open-vsx.org/extension/TabbyML/vscode-tabby)
 * [VIM Extension](https://github.com/TabbyML/tabby/tree/main/clients/vim)
-
-## API
-Tabby has opened a FastAPI server at [localhost:8080](https://localhost:8080), which includes an OpenAPI documentation of the HTTP API. The same API documentation is also hosted at [here](/api).

website/docs/self-hosting/01-docker.md

@@ -0,0 +1,59 @@
+# Docker
+
+There is a supplied docker image to make deploying a server as a container easier.
+
+
+## CPU
+
+**Command line**
+```bash
+docker run \
+  -p 8080:8080 -v $HOME/.tabby:/data \
+  tabbyml/tabby serve --model TabbyML/SantaCoder-1B
+```
+
+
+**Docker Compose**
+```yaml
+version: '3.5'
+
+services:
+  tabby:
+    restart: always
+    image: tabbyml/tabby
+    command: serve --model TabbyML/SantaCoder-1B
+    volumes:
+      - "$HOME/.tabby:/data"
+    ports:
+      - 8080:8080
+```
+
+## CUDA (requires NVIDIA Container Toolkit)
+
+**Command line**
+```bash
+docker run \
+  --gpus all -p 8080:8080 -v $HOME/.tabby:/data \
+  tabbyml/tabby \
+  serve --model TabbyML/SantaCoder-1B --device cuda
+```
+
+**Docker Compose**
+```yaml
+version: '3.5'
+services:
+  tabby:
+    restart: always
+    image: tabbyml/tabby
+    command: serve --model TabbyML/SantaCoder-1B --device cuda
+    volumes:
+      - "$HOME/.tabby:/data"
+    ports:
+      - 8080:8080
+    resources:
+    reservations:
+      devices:
+      - driver: nvidia
+        count: 1
+        capabilities: [gpu]
+```

website/docs/self-hosting/02-apple.md

@@ -0,0 +1,9 @@
+# Mac M1/M2 (Preview)
+
+Thanks to Apple's Accelerate and CoreML frameworks, we can now run Tabby on edge devices with reasonable inference speed. Follow the steps below to set it up:
+
+1. Download the `tabby` binary from the Release page [here](https://github.com/TabbyML/tabby/releases/tag/latest).
+
+2. Run `tabby --help` to verify successful installation.
+
+3. Start the server with `tabby serve model --models TabbyML/T5P-220M`.

website/docs/self-hosting/self-hosting.md

@@ -0,0 +1,17 @@
+# Self Hosting
+
+## Configuration
+
+Server config can be found at `~/.tabby/config.toml`
+
+it looks something like this
+
+```toml
+[[repositories]]
+git_url = "https://github.com/TabbyML/tabby.git"
+```
+
+| Parameter                 | Description                                                                         |
+| ------------------------- | ----------------------------------------------------------------------------------- |
+| `repository`              | List of source code repository to integrate with the instance.                      |
+| `repository.git_url`      | URL to git repository, where tabby extract snippets for prompting and fine tuning.  |

website/docs/server.md

@@ -1,48 +0,0 @@
-# Server
-
-## Docker
-
-We recommend adding the following aliases to your `.bashrc` or `.zshrc` file:
-
-```shell
-# Save aliases to bashrc / zshrc
-alias tabby="docker run -u $(id -u) -p 8080:8080 -v $HOME/.tabby:/data tabbyml/tabby"
-
-# Alias for GPU (requires NVIDIA Container Toolkit)
-alias tabby-gpu="docker run --gpus all -u $(id -u) -p 8080:8080 -v $HOME/.tabby:/data tabbyml/tabby"
-```
-
-After adding these aliases, you can use the `tabby` command as usual. Here are some examples of its usage:
-
-```shell
-# Create work directory for tabby
-mkdir -p $HOME/.tabby
-
-# Usage
-tabby --help
-
-# Serve the model
-tabby serve --model TabbyML/J-350M
-
-# Serve with cuda
-tabby-gpu serve --model TabbyML/J-350M --device cuda
-```
-
-## Configuration
-
-Tabby maintains its runtime data in `~/.tabby`, with `~/.tabby/config.toml` serving as its configuration file.
-
-You can modify the path to the data directory by setting the `TABBY_ROOT` variable. For example:
-
-```
-export TABBY_ROOT=/data/tabby
-```
-
-## Example `~/.tabby/config.toml`
-
-```toml
-[[repositories]]
-git_url = "https://github.com/TabbyML/tabby.git"
-```
-
-`repositories` is a list of git repositories integrated into Tabby for prompting/fine-tuning.