git/gemma3-vllm-stack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update docs, configs, and scripts

Browse Source 
Co-Authored-By: Oz <oz-agent@warp.dev>
This commit is contained in:
Raghav
2026-04-19 09:42:52 +05:30
parent 12b66edd22
commit 319881a09f
11 changed files with 157 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
scripts/install.sh
View File

@ -4,15 +4,49 @@ 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
' "$*"
printf '[install] %s\n' "$*"
}
err() {
printf '[install][error] %s
' "$*" >&2
printf '[install][error] %s\n' "$*" >&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() {
@ -39,7 +73,8 @@ install_docker_ubuntu() {
local codename
codename="${VERSION_CODENAME:-jammy}"
echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu ${codename} stable" | sudo tee /etc/apt/sources.list.d/docker.list >/dev/null
echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu ${codename} stable" \
| sudo tee /etc/apt/sources.list.d/docker.list >/dev/null
sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
@ -89,23 +124,17 @@ check_or_install_docker() {
}
prepare_env_files() {
if [[ ! -f "${REPO_ROOT}/.env" ]]; then
cp "${REPO_ROOT}/.env.example" "${REPO_ROOT}/.env"
if [[ ! -f "${ENV_FILE}" ]]; then
cp "${REPO_ROOT}/.env.example" "${ENV_FILE}"
log "Created .env from .env.example."
err "IMPORTANT: edit .env and set HF_TOKEN (and optionally VLLM_API_KEY) before production use."
err "IMPORTANT: edit .env and set HF_TOKEN, VLLM_API_KEY, GEMMA_MODEL_ID, and other values before production use."
fi
if [[ ! -f "${REPO_ROOT}/backend/config/model.env" ]]; then
cp "${REPO_ROOT}/backend/config/model.env.example" "${REPO_ROOT}/backend/config/model.env"
log "Created backend/config/model.env from example."
fi
mkdir -p "${REPO_ROOT}/backend/config" "${REPO_ROOT}/frontend/config" "${REPO_ROOT}/models" "${REPO_ROOT}/frontend/data/open-webui"
if [[ ! -f "${REPO_ROOT}/frontend/config/frontend.env" ]]; then
cp "${REPO_ROOT}/frontend/config/frontend.env.example" "${REPO_ROOT}/frontend/config/frontend.env"
log "Created frontend/config/frontend.env from example."
fi
mkdir -p "${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() {
@ -117,27 +146,24 @@ warn_if_rocm_devices_missing() {
start_stack() {
log "Pulling container images."
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${REPO_ROOT}/.env" pull
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" pull
log "Starting containers in detached mode."
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${REPO_ROOT}/.env" up -d
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="$(grep -E '^BACKEND_PORT=' "${REPO_ROOT}/.env" | tail -n1 | cut -d'=' -f2 || true)"
frontend_port="$(grep -E '^FRONTEND_PORT=' "${REPO_ROOT}/.env" | tail -n1 | cut -d'=' -f2 || true)"
backend_port="${backend_port:-8000}"
frontend_port="${frontend_port:-3000}"
backend_port="${BACKEND_PORT:-8000}"
frontend_port="${FRONTEND_PORT:-3000}"
log "Backend status:"
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${REPO_ROOT}/.env" ps gemma3-vllm || true
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" ps gemma3-vllm || true
log "Frontend status:"
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${REPO_ROOT}/.env" ps chat-ui || true
docker compose -f "${REPO_ROOT}/docker-compose.yml" --env-file "${ENV_FILE}" ps chat-ui || true
printf '
'
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"