#!/usr/bin/env bash
# Serve the FastFlowLM (FLM) NPU endpoint — frank-default-npu.
#
# Runs flm serve with the model tag in frank-default-npu.env. The NPU
# (XDNA2, 50 TOPS) is a single-lane device: generations serialize in FIFO
# order, so this is a background/triage endpoint. The NPU shares the ~30 GiB
# unified pool with frank-default-large (the CIRU llama.cpp service on the
# iGPU); see serverAppConfigs-docs/FastFlowLM NPU Inference.md for the memory budget.
#
# NOTE: FLM requires unlimited memlock. The unit sets LimitMEMLOCK=infinity.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FLM_NPU_ENV_FILE:-$SCRIPT_DIR/frank-default-npu.env}"
if [[ -f "$ENV_FILE" ]]; then
    set -a
    # shellcheck disable=SC1090
    source "$ENV_FILE"
    set +a
fi

# --- defaults (used when the env file does not set them) -------------------
: "${FLM_BIN:=/usr/bin/flm}"
: "${FLM_MODEL:=gemma4-it:e4b}"
: "${FLM_HOST:=0.0.0.0}"
: "${FLM_PORT:=52626}"
: "${FLM_PMODE:=performance}"
: "${FLM_ASR:=0}"
: "${FLM_CTX_LEN:=-1}"

if [[ ! -x "$FLM_BIN" ]]; then
    echo "missing flm binary: $FLM_BIN" >&2
    exit 1
fi

# --- optional flags ----------------------------------------------------------
OPT_ARGS=()
if [[ "${FLM_ASR}" != "0" ]]; then
    OPT_ARGS+=(-a "${FLM_ASR}")
fi
if [[ "${FLM_CTX_LEN}" != "-1" ]]; then
    OPT_ARGS+=(-c "${FLM_CTX_LEN}")
fi

exec "$FLM_BIN" serve "$FLM_MODEL" \
    --host "$FLM_HOST" \
    -p "$FLM_PORT" \
    --pmode "$FLM_PMODE" \
    "${OPT_ARGS[@]}"