diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml
deleted file mode 100644
index b56bc7d..0000000
--- a/.github/workflows/docker.yml
+++ /dev/null
@@ -1,91 +0,0 @@
-name: Create and publish docker image
-
-on:
-  workflow_dispatch:
-  push:
-    branches: [ "main" ]
-    paths:
-      - 'poetry.lock'
-      - 'tabby/**'
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-      # This is used to complete the identity challenge
-      # with sigstore/fulcio when running outside of PRs.
-      id-token: write
-
-    steps:
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # if set to "true" but frees about 6 GB
-          tool-cache: true
-
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: false
-          swap-storage: true
-
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      # Workaround: https://github.com/docker/build-push-action/issues/461
-      - name: Setup Docker buildx
-        uses: docker/setup-buildx-action@v2.0.0
-
-      # Login against a Docker registry except on PR
-      # https://github.com/docker/login-action
-      - name: Log into GitHub Container registry
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v2.0.0
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Log into Docker Hub
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v2.0.0
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Generate image name
-        run: |
-          echo "IMAGE_NAME=${GITHUB_REPOSITORY,,}" >>${GITHUB_ENV}
-
-      - uses: int128/docker-build-cache-config-action@v1
-        id: cache
-        with:
-          image: ghcr.io/${{ env.IMAGE_NAME }}/cache
-
-      # Build and push Docker image with Buildx (don't push on PR)
-      # https://github.com/docker/build-push-action
-      - name: Build and push Docker image
-        id: build-and-push
-        uses: docker/build-push-action@v3.1.1
-        with:
-          file: Dockerfile
-          context: .
-          push: ${{ github.event_name != 'pull_request' }}
-          tags: |
-            ghcr.io/${{ env.IMAGE_NAME }}:latest
-            ${{ env.IMAGE_NAME }}:latest
-          cache-from: ${{ steps.cache.outputs.cache-from }}
-          cache-to: ${{ steps.cache.outputs.cache-to }}
-
-      - name: Docker Hub Description
-        uses: peter-evans/dockerhub-description@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-          repository: tabbyml/tabby
diff --git a/Dockerfile b/Dockerfile
deleted file mode 100644
index 6d381d6..0000000
--- a/Dockerfile
+++ /dev/null
@@ -1,73 +0,0 @@
-# syntax = docker/dockerfile:1.5
-
-FROM tabbyml/fastertransformer_backend
-
-RUN apt update && apt -y install build-essential libssl-dev zlib1g-dev \
-  libbz2-dev libreadline-dev libsqlite3-dev curl \
-  libncursesw5-dev xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev
-
-RUN mkdir -p /home/app
-RUN chown 1000 /home/app
-
-USER 1000
-WORKDIR /home/app
-ENV HOME /home/app
-
-# Setup pyenv
-RUN git clone --depth=1 https://github.com/pyenv/pyenv.git .pyenv
-ENV PATH="$HOME/.pyenv/shims:/home/app/.pyenv/bin:$PATH"
-
-ARG PYTHON_VERSION=3.10.10
-RUN pyenv install ${PYTHON_VERSION}
-RUN pyenv global ${PYTHON_VERSION}
-
-ARG PYPI_INDEX_URL=https://pypi.org/simple
-ARG POETRY_VERSION=1.4.0
-
-RUN --mount=type=cache,target=$HOME/.cache pip install -i $PYPI_INDEX_URL "poetry==$POETRY_VERSION"
-
-# vector
-RUN <<EOF
-curl --proto '=https' --tlsv1.2 -sSf https://sh.vector.dev | bash -s -- -y
-EOF
-ENV PATH "$HOME/.vector/bin:$PATH"
-
-# Supervisord
-RUN --mount=type=cache,target=$HOME/.cache pip install -i $PYPI_INDEX_URL supervisor
-
-RUN mkdir -p ~/.bin
-ENV PATH "$HOME/.bin:$PATH"
-
-# Install dagu
-RUN <<EOF
-  curl -L https://github.com/yohamta/dagu/releases/download/v1.10.2/dagu_1.10.2_Linux_x86_64.tar.gz > dagu.tar.gz
-  tar zxvf dagu.tar.gz
-  mv dagu ~/.bin/
-  rm dagu.tar.gz LICENSE.md README.md
-EOF
-
-# Install tabby dependencies
-COPY poetry.lock pyproject.toml ./
-RUN poetry export --without-hashes > requirements.txt
-RUN --mount=type=cache,target=$HOME/.cache pip install -i $PYPI_INDEX_URL --no-dependencies -r requirements.txt
-
-COPY tabby ./tabby
-
-# Install caddy
-RUN <<EOF
-  curl -L "https://github.com/caddyserver/caddy/releases/download/v2.6.4/caddy_2.6.4_linux_amd64.tar.gz" -o caddy.tar.gz
-  tar zxvf caddy.tar.gz
-  mv caddy ~/.bin/
-  rm caddy.tar.gz README.md LICENSE
-EOF
-
-# Setup file permissions
-USER root
-RUN mkdir -p /var/lib/vector
-RUN chown 1000 /var/lib/vector
-
-RUN mkdir -p $HOME/.cache
-RUN chown 1000 $HOME/.cache
-
-USER 1000
-CMD ["./tabby/scripts/tabby.sh"]
diff --git a/deployment/.env b/deployment/.env
deleted file mode 100644
index ceae966..0000000
--- a/deployment/.env
+++ /dev/null
@@ -1,5 +0,0 @@
-MODEL_NAME=TabbyML/J-350M
-
-# Volumes
-DATA_VOLUME="../data:/data"
-HF_VOLUME="../data/hf_cache:/home/app/.cache/huggingface"
diff --git a/deployment/docker-compose.triton.yml b/deployment/docker-compose.triton.yml
deleted file mode 100644
index e52a79b..0000000
--- a/deployment/docker-compose.triton.yml
+++ /dev/null
@@ -1,15 +0,0 @@
-version: '3.3'
-
-services:
-  tabby:
-    shm_size: 1gb
-    environment:
-      MODEL_BACKEND: triton
-      MODEL_REPLICA: ${MODEL_REPLICA:-1}
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: all
-              capabilities: [gpu]
diff --git a/deployment/docker-compose.yml b/deployment/docker-compose.yml
deleted file mode 100644
index 0090dfa..0000000
--- a/deployment/docker-compose.yml
+++ /dev/null
@@ -1,29 +0,0 @@
-version: '3.3'
-
-services:
-  init:
-    image: tabbyml/tabby
-    container_name: init
-    user: root
-    volumes:
-      - ${DATA_VOLUME}
-      - ${HF_VOLUME}
-    command: chown -R 1000 /data
-
-  tabby:
-    image: tabbyml/tabby
-    container_name: tabby
-    environment:
-      MODEL_NAME: ${MODEL_NAME}
-    ports:
-      - "5000:5000"
-    volumes:
-      - ${DATA_VOLUME}
-      - ${HF_VOLUME}
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:5000"]
-      interval: 2s
-      timeout: 2s
-      start_period: 1200s
-    depends_on:
-      - init
diff --git a/deployment/skypilot/README.md b/deployment/skypilot/README.md
deleted file mode 100644
index 217c1e3..0000000
--- a/deployment/skypilot/README.md
+++ /dev/null
@@ -1,50 +0,0 @@
-# Run Tabby server on any cloud with one click
-
-## Background
-
-[**SkyPilot**](https://github.com/skypilot-org/skypilot) is an open-source framework for seamlessly running machine learning on any cloud. With a simple CLI, users can easily launch many clusters and jobs, while substantially lowering their cloud bills. Currently, [Lambda Labs](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#lambda-cloud) (low-cost GPU cloud), [AWS](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#aws), [GCP](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#gcp), and [Azure](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#azure) are supported. See [docs](https://skypilot.readthedocs.io/en/latest/) to learn more.
-
-## Steps
-
-1. Install SkyPilot and [check that cloud credentials exist](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html#cloud-account-setup):
-    ```bash
-    pip install "skypilot[aws,gcp,azure,lambda]"  # pick your clouds
-    sky check
-    ```
-    <img src="https://i.imgur.com/7BUci5n.png" width="485" alt="`sky check` output showing enabled clouds for SkyPilot"/>
-
-2. Get the [deployment folder](./):
-    ```bash
-    git clone https://github.com/TabbyML/tabby
-    cd tabby/deployment/skypilot
-    ```
-
-3. run:
-    ```bash
-    sky launch -c tabby default.yml
-    ```
-
-4. Open another terminal and run:
-    ```bash
-    ssh -L 5000:localhost:5000 tabby
-    ```
-
-5. Open http://localhost:5000 in your browser and start coding!
-![tabby admin server](https://user-images.githubusercontent.com/388154/227792390-ec19e9b9-ebbb-4a94-99ca-8a142ffb5e46.png)
-
-## Cleaning up
-When you are done, you can stop or tear down the cluster:
-
-- **To stop the cluster**, run
-    ```bash
-    sky stop tabby # or pass your custom name if you used "-c <other name>"
-    ```
-    You can restart a stopped cluster and relaunch the chatbot (the `run` section in YAML) with
-    ```bash
-    sky launch default.yml -c tabby --no-setup
-    ```
-    Note the `--no-setup` flag: a stopped cluster preserves its disk contents so we can skip redoing the setup.
-- **To tear down the cluster** (non-restartable), run
-    ```bash
-    sky down tabby # or pass your custom name if you used "-c <other name>"
-    ```
diff --git a/deployment/skypilot/default.yml b/deployment/skypilot/default.yml
deleted file mode 100644
index 6e1aa06..0000000
--- a/deployment/skypilot/default.yml
+++ /dev/null
@@ -1,25 +0,0 @@
-resources:
-  accelerators: A100:1
-  disk_size: 1024
-
-setup: |
-  set -ex
-
-  # On some cloud providers, docker-compose is not installed by default.
-  sudo curl -L https://github.com/docker/compose/releases/download/v2.17.2/docker-compose-linux-x86_64 -o /usr/local/bin/docker-compose
-  sudo chmod a+x /usr/local/bin/docker-compose
-
-  # Pull tabby images.
-  git clone https://github.com/TabbyML/tabby.git || true
-  cd tabby/deployment
-
-  # On certain cloud providers (e.g lambda cloud), the default user is not added to docker group, so we need sudo here
-  sudo docker-compose pull
-
-  # Add current user to docker group, it won't take effect immediately as skypilot job is started by a long-running daemon.
-  sudo usermod -aG docker $USER
-
-
-run: |
-  cd tabby/deployment
-  sudo MODEL_REPLICA=${MODEL_REPLICA:-8} docker-compose -f docker-compose.yml -f docker-compose.triton.yml up
diff --git a/development/.gitignore b/development/.gitignore
deleted file mode 100644
index 1269488..0000000
--- a/development/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-data
diff --git a/development/Dockerfile b/development/Dockerfile
deleted file mode 100644
index cefa0ef..0000000
--- a/development/Dockerfile
+++ /dev/null
@@ -1,3 +0,0 @@
-FROM tabbyml/tabby
-
-ARG PYPI_INDEX_URL=https://pypi.org/simple
diff --git a/development/Makefile b/development/Makefile
deleted file mode 100644
index 770edf0..0000000
--- a/development/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-DEFAULT :=
-UP_FLAGS := up --remove-orphans
-
-build:
-	docker-compose -f ../deployment/docker-compose.yml -f docker-compose.dev.yml build
-
-dev:
-	docker-compose -f ../deployment/docker-compose.yml -f docker-compose.dev.yml $(UP_FLAGS)
-
-dev-triton:
-	docker-compose -f ../deployment/docker-compose.yml -f ../deployment/docker-compose.triton.yml -f docker-compose.dev.yml $(UP_FLAGS)
diff --git a/development/docker-compose.dev.yml b/development/docker-compose.dev.yml
deleted file mode 100644
index ed9d046..0000000
--- a/development/docker-compose.dev.yml
+++ /dev/null
@@ -1,21 +0,0 @@
-version: '3.3'
-
-services:
-  tabby:
-    image: tabbyml/tabby:dev
-    build:
-      context: ..
-      dockerfile: ./development/Dockerfile
-      args:
-        PYPI_INDEX_URL: https://mirrors.aliyun.com/pypi/simple
-    environment:
-      UVICORN_RELOAD: true
-      VECTOR_WATCH_CONFIG: true
-      STREAMLIT_RUN_ON_SAVE: true
-      CADDY_WATCH_CONFIG: true
-      STREAMLIT_HIDE_MENU: false
-    volumes:
-      - ../tabby:/home/app/tabby
-    ports:
-      - 8083:8083
-      - 8084:8084