forked from sagnik/Project_Velocity
sagnik
6cdc366718
Co-authored-by: Sagnik <sagnik7896@gmail.com> Reviewed-on: sagnik/Project_Velocity#33
96 lines
2.7 KiB
Bash
96 lines
2.7 KiB
Bash
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
# NemoClaw deployment helper for the Desineuron SGLang runtime.
|
|
# This script intentionally avoids Ollama-era assumptions and configures
|
|
# NemoClaw/OpenShell to talk to the shared OpenAI-compatible SGLang endpoint.
|
|
|
|
NVME_ROOT="${NVME_ROOT:-/opt/dlami/nvme/nemoclaw}"
|
|
SGLANG_BASE_URL="${SGLANG_BASE_URL:-https://llm.desineuron.in}"
|
|
SGLANG_MODEL="${SGLANG_MODEL:-qwen3.6:35b-a3b}"
|
|
SGLANG_API_TOKEN="${SGLANG_API_TOKEN:-}"
|
|
OPENSHELL_PORT="${OPENSHELL_PORT:-8080}"
|
|
AGENT_NAME="${AGENT_NAME:-velocity-sentinel}"
|
|
|
|
if [[ "${EUID}" -ne 0 ]]; then
|
|
echo "Run this script with sudo or as root."
|
|
exit 1
|
|
fi
|
|
|
|
echo "==> Desineuron NemoClaw deploy"
|
|
echo "NVME root : ${NVME_ROOT}"
|
|
echo "SGLang base URL: ${SGLANG_BASE_URL}"
|
|
echo "Model : ${SGLANG_MODEL}"
|
|
echo "Agent : ${AGENT_NAME}"
|
|
|
|
mkdir -p "${NVME_ROOT}"/{logs,state,home}
|
|
|
|
if ! command -v node >/dev/null 2>&1; then
|
|
curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
|
|
apt-get update -y
|
|
apt-get install -y nodejs
|
|
fi
|
|
|
|
if ! command -v docker >/dev/null 2>&1; then
|
|
apt-get update -y
|
|
apt-get install -y docker.io
|
|
systemctl enable --now docker
|
|
fi
|
|
|
|
if ! command -v openshell >/dev/null 2>&1; then
|
|
npm install -g @nvidia/openshell || true
|
|
fi
|
|
|
|
if ! command -v nemoclaw >/dev/null 2>&1; then
|
|
npm install -g @nvidia/nemoclaw || true
|
|
fi
|
|
|
|
cat >/etc/default/desineuron-nemoclaw <<EOF
|
|
SGLANG_BASE_URL=${SGLANG_BASE_URL}
|
|
SGLANG_MODEL=${SGLANG_MODEL}
|
|
SGLANG_API_TOKEN=${SGLANG_API_TOKEN}
|
|
NEMOCLAW_BASE_URL=${SGLANG_BASE_URL}
|
|
NEMOCLAW_MODEL=${SGLANG_MODEL}
|
|
NEMOCLAW_API_TOKEN=${SGLANG_API_TOKEN}
|
|
EOF
|
|
chmod 600 /etc/default/desineuron-nemoclaw
|
|
|
|
if command -v openshell >/dev/null 2>&1; then
|
|
openshell inference set \
|
|
--provider compatible-endpoint \
|
|
--base-url "${SGLANG_BASE_URL}/v1" \
|
|
--api-key "${SGLANG_API_TOKEN:-desineuron}" \
|
|
--model "${SGLANG_MODEL}" \
|
|
--context-window 8192 \
|
|
--max-tokens 4096 || true
|
|
fi
|
|
|
|
cat >/etc/systemd/system/desineuron-nemoclaw-gateway.service <<EOF
|
|
[Unit]
|
|
Description=Desineuron NemoClaw Gateway
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
EnvironmentFile=/etc/default/desineuron-nemoclaw
|
|
WorkingDirectory=${NVME_ROOT}
|
|
Environment=HOME=${NVME_ROOT}/home
|
|
ExecStart=/usr/bin/env bash -lc 'nemoclaw serve --name ${AGENT_NAME} --port ${OPENSHELL_PORT}'
|
|
Restart=always
|
|
RestartSec=5
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|
|
EOF
|
|
|
|
systemctl daemon-reload
|
|
systemctl enable --now desineuron-nemoclaw-gateway.service
|
|
systemctl --no-pager --full status desineuron-nemoclaw-gateway.service
|
|
|
|
echo
|
|
echo "NemoClaw deployment complete."
|
|
echo "Gateway port : ${OPENSHELL_PORT}"
|
|
echo "Model : ${SGLANG_MODEL}"
|
|
echo "Runtime : ${SGLANG_BASE_URL}/v1"
|