#!/usr/bin/env bash
# Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
# The deployment uses a standalone MTP draft head and f16 KV cache.
#
# The Qwen-Sharp chat template (scripts/chat-template.jinja) is applied at
# runtime so the model emits reasoning in DeepSeek format; the reasoning
# trail is preserved across turns via CHAT_TEMPLATE_KWARGS.
set -euo pipefail

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

# --- defaults (used when the env file does not set them) -------------------
: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
: "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
: "${CHAT_TEMPLATE_KWARGS:={}}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=262144}"
: "${PARALLEL:=1}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=4096}"
: "${NUM_THREADS:=16}"
: "${THREAD_BATCH:=32}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
: "${MTP_N_MAX:=4}"
: "${MTP_N_MIN:=0}"
: "${MTP_P_MIN:=0.0}"
: "${MTP_P_SPLIT:=0.10}"
: "${TEMPERATURE:=0.7}"
: "${TOP_K:=20}"
: "${TOP_P:=0.8}"
: "${MIN_P:=0.0}"
: "${PRESENCE_PENALTY:=1.5}"
: "${REASONING:=off}"
: "${REASONING_FORMAT:=none}"
: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"

MODEL="$MODEL_DIR/$MODEL_FILE"
for f in "$LLAMA_BIN" "$MODEL" "$MTP_DRAFT_FILE" "$MODEL_DIR/$MMPROJ_FILE" "$CHAT_TEMPLATE_FILE"; do
    if [[ ! -r "$f" ]]; then
        echo "missing or unreadable required artifact: $f" >&2
        exit 1
    fi
done
if [[ ! -x "$LLAMA_BIN" ]]; then
    echo "missing executable runtime: $LLAMA_BIN" >&2
    exit 1
fi
SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
ROCM_PATH="${ROCM_DEVEL:-${ROCM_PATH:-/opt/rocm}}"
if [[ -n "${ROCM_LIB:-}" && -n "${ROCM_CORE:-}" ]]; then
    LIBRARY_PATH="$ROCM_LIB/lib:$ROCM_CORE/lib:$ROCM_DEVEL/lib/llvm/lib:$SERVER_DIR:${LD_LIBRARY_PATH:-}"
else
    LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
fi

exec /usr/bin/env \
    ROCM_PATH="$ROCM_PATH" \
    HIP_VISIBLE_DEVICES=0 \
    LD_LIBRARY_PATH="$LIBRARY_PATH" \
    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
    GGML_CUDA_GRAPH_OPT=0 \
    LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
    LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \
    "$LLAMA_BIN" \
    --model "$MODEL" \
    --alias "$ALIAS" \
    --chat-template-file "$CHAT_TEMPLATE_FILE" \
    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    --jinja \
    --device ROCm0 \
    --gpu-layers 999 \
    --parallel "$PARALLEL" \
    --ctx-size "$CTX_SIZE" \
    --batch-size "$BATCH_SIZE" \
    --ubatch-size "$UBATCH_SIZE" \
    --flash-attn on \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --threads "$NUM_THREADS" \
    --threads-batch "$THREAD_BATCH" \
    --ctx-checkpoints "$CTX_CHECKPOINTS" \
    --cache-ram "$CACHE_RAM" \
    --cache-prompt \
    --cache-idle-slots \
    --metrics \
    --spec-type draft-mtp \
    --model-draft "$MTP_DRAFT_FILE" \
    --mmproj "$MODEL_DIR/$MMPROJ_FILE" \
    --spec-draft-device ROCm0 \
    --spec-draft-ngl 999 \
    --spec-draft-type-k "$CACHE_TYPE_K" \
    --spec-draft-type-v "$CACHE_TYPE_V" \
    --spec-draft-n-max "$MTP_N_MAX" \
    --spec-draft-n-min "$MTP_N_MIN" \
    --spec-draft-p-min "$MTP_P_MIN" \
    --spec-draft-p-split "$MTP_P_SPLIT" \
    --spec-draft-backend-sampling \
    --temp "$TEMPERATURE" \
    --top-p "$TOP_P" \
    --top-k "$TOP_K" \
    --min-p "$MIN_P" \
    --presence-penalty "$PRESENCE_PENALTY" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1