#!/usr/bin/env bash
# Start SGLang server for the P800 long-context matrix.
# Usage: start_server.sh <context_length> <max_running>
set -Eeuo pipefail

CONTEXT_LENGTH="${1:-80000}"
MAX_RUNNING="${2:-64}"

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"

# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../scripts/common/server_docker.sh"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/config.env"

log_init "${RESULT_ROOT:-/tmp/${EXPERIMENT_NAME}}/logs/start_server.log"
log "starting server for ${EXPERIMENT_NAME}"
log "model: ${MODEL_PATH}"
log "port: ${PORT}"
log "server mode: ${SERVER_MODE}"
log "context length: ${CONTEXT_LENGTH}"
log "max running requests: ${MAX_RUNNING}"

extra_args="--context-length ${CONTEXT_LENGTH} --max-running-requests ${MAX_RUNNING} --mem-fraction-static 0.85"
export SGLANG_EXTRA_LAUNCH_ARGS="${SGLANG_EXTRA_LAUNCH_ARGS:-${extra_args}}"

docker_server_start "${MODEL_PATH}" "${PORT}" "${LOG_DIR}/server.outer.log" "${SERVER_MODE}" "${SGLANG_EXTRA_LAUNCH_ARGS}"