Files
gemma3-vllm-stack/scripts/install.sh
2026-04-19 09:42:52 +05:30

182 lines
5.2 KiB
Bash
Executable File

#!/usr/bin/env bash
# Installs prerequisites (if needed), prepares config files, and starts Gemma 3 + vLLM + chat UI stack.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
ENV_FILE="${REPO_ROOT}/.env"
log() {
printf '[install] %s\n' "$*"
}
err() {
printf '[install][error] %s\n' "$*" >&2
}
load_env_file() {
if [[ ! -f "${ENV_FILE}" ]]; then
return
fi
set -a
# shellcheck disable=SC1090
source "${ENV_FILE}"
set +a
: "${GEMMA_MODEL_ID:?GEMMA_MODEL_ID must be set in .env}"
}
sync_service_env_files() {
cat > "${REPO_ROOT}/backend/config/model.env" <<EOF
HF_TOKEN=${HF_TOKEN:-YOUR_HF_TOKEN_HERE}
VLLM_API_KEY=${VLLM_API_KEY:-YOUR_LOCAL_API_KEY_HERE}
GEMMA_MODEL_ID=${GEMMA_MODEL_ID}
BACKEND_PORT=${BACKEND_PORT:-8000}
HUGGINGFACE_CACHE_DIR=${HUGGINGFACE_CACHE_DIR:-/home/${USER}/.cache/huggingface}
VLLM_MAX_MODEL_LEN=${VLLM_MAX_MODEL_LEN:-512}
VLLM_GPU_MEMORY_UTILIZATION=${VLLM_GPU_MEMORY_UTILIZATION:-0.7}
EOF
cat > "${REPO_ROOT}/frontend/config/frontend.env" <<EOF
FRONTEND_PORT=${FRONTEND_PORT:-3000}
OPENAI_API_BASE_URL=${OPENAI_API_BASE_URL:-http://gemma3-vllm:8000/v1}
VLLM_API_KEY=${VLLM_API_KEY:-YOUR_LOCAL_API_KEY_HERE}
GEMMA_MODEL_ID=${GEMMA_MODEL_ID}
OPEN_WEBUI_DATA_DIR=${OPEN_WEBUI_DATA_DIR:-./frontend/data/open-webui}
EOF
log "Synced backend/config/model.env and frontend/config/frontend.env from .env."
}
require_linux() {
if [[ "$(uname -s)" != "Linux" ]]; then
err "This script supports Linux only."
exit 1
fi
}
install_docker_ubuntu() {
log "Installing Docker Engine and Compose plugin using official Docker apt repository."
sudo apt-get update
sudo apt-get install -y ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
if [[ ! -f /etc/apt/keyrings/docker.gpg ]]; then
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg
fi
source /etc/os-release
local arch
arch="$(dpkg --print-architecture)"
local codename
codename="${VERSION_CODENAME:-jammy}"
echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu ${codename} stable" \
| sudo tee /etc/apt/sources.list.d/docker.list >/dev/null
sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
if ! sudo systemctl is-active --quiet docker; then
sudo systemctl enable --now docker
fi
if ! getent group docker >/dev/null; then
sudo groupadd docker
fi
if ! id -nG "${USER}" | grep -qw docker; then
sudo usermod -aG docker "${USER}"
log "Added ${USER} to docker group. You may need to log out and back in for group membership to apply."
fi
}
check_or_install_docker() {
local have_docker=1
local have_compose=1
if ! command -v docker >/dev/null 2>&1; then
have_docker=0
fi
if ! docker compose version >/dev/null 2>&1; then
have_compose=0
fi
if [[ ${have_docker} -eq 1 && ${have_compose} -eq 1 ]]; then
log "Docker and Compose plugin are already available."
return
fi
if [[ -f /etc/os-release ]]; then
source /etc/os-release
if [[ "${ID:-}" == "ubuntu" ]]; then
install_docker_ubuntu
return
fi
fi
err "Docker/Compose missing and automatic installation is implemented for Ubuntu only."
err "See docs/TROUBLESHOOTING.md#docker-and-compose-not-available"
exit 1
}
prepare_env_files() {
if [[ ! -f "${ENV_FILE}" ]]; then
cp "${REPO_ROOT}/.env.example" "${ENV_FILE}"
log "Created .env from .env.example."
err "IMPORTANT: edit .env and set HF_TOKEN, VLLM_API_KEY, GEMMA_MODEL_ID, and other values before production use."
fi
mkdir -p "${REPO_ROOT}/backend/config" "${REPO_ROOT}/frontend/config" "${REPO_ROOT}/models" "${REPO_ROOT}/frontend/data/open-webui"
load_env_file
log "Using GEMMA_MODEL_ID=${GEMMA_MODEL_ID}"
sync_service_env_files
}
warn_if_rocm_devices_missing() {
if [[ ! -e /dev/kfd || ! -d /dev/dri ]]; then
err "ROCm device files /dev/kfd or /dev/dri are not available."
err "See docs/TROUBLESHOOTING.md#rocm-devices-not-visible-in-host"
fi
}
start_stack() {
log "Pulling container images."
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" pull
log "Starting containers in detached mode."
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" up -d --force-recreate
}
show_status_and_urls() {
local backend_port frontend_port
backend_port="${BACKEND_PORT:-8000}"
frontend_port="${FRONTEND_PORT:-3000}"
log "Backend status:"
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" ps gemma3-vllm || true
log "Frontend status:"
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" ps chat-ui || true
printf '\n'
log "API endpoint: http://localhost:${backend_port}/v1"
log "Chat UI endpoint: http://localhost:${frontend_port}"
log "If startup fails, inspect logs with: docker compose logs --tail=200 gemma3-vllm chat-ui"
}
main() {
require_linux
check_or_install_docker
prepare_env_files
warn_if_rocm_devices_missing
start_stack
show_status_and_urls
}
main "$@"