#!/usr/bin/env bash
# Start SGLang multi-node TP=16 EP=2 across 2 nodes through the shared
# deployment layer (`python -m sskj.deploy start`, NODE_HOSTS orchestration).
# Usage: start_sglang_multinode.sh [--dry-run]
set -Eeuo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/config.env"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../../scripts/common/deploy_cli.sh"

RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
mkdir -p "${RUNTIME_BASE}/logs"

DRY_RUN="${DRY_RUN:-0}"
DEPLOY_PROFILE="${DEPLOY_PROFILE:-pro6000/dsv4_pro6000_sglang_tp16}"

log "=== SGLang multi-node TP=${TP_SIZE} EP=${EP_SIZE} via deploy profile ${DEPLOY_PROFILE} ==="

if [[ "$DRY_RUN" == "1" ]]; then
  PYTHONPATH="${ROOT_DIR}/src" "${DEPLOY_PYTHON:-python3}" -m sskj.deploy start \
    --profile "$(deploy_profile_abs "$DEPLOY_PROFILE")" \
    --tp "$TP_SIZE" --dp "1" \
    --port "${SGLANG_PORT:-30000}" \
    --model-path "$MODEL_PATH" \
    --log-dir "${RUNTIME_BASE}/logs" \
    --dry-run
else
  deploy_start_multinode \
    "$DEPLOY_PROFILE" "$TP_SIZE" "1" \
    "${RUNTIME_BASE}/logs" \
    "${SGLANG_PORT:-30000}" \
    "$MODEL_PATH" \
    "$EXPERIMENT"
fi