#!/usr/bin/env bash
# Serve caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded MTP) as
# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
# (ROCmI4 W4A4) on Dankclaw (Strix Halo gfx1151).
#
# Runtime: charlie12345/ROCmFPX pinned at commit
# c49ebdbd5c9f01ec242369f9e7f7967855f80cba, built with
# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4,
# amdclang 22). The model has an embedded NextN/MTP head in the main GGUF, so
# a separate draft file is not loaded; the MTP draft runs on ROCm0 with all
# layers via --spec-draft-ngl all.
#
# The qualified MTP profile is strict Qwen MTP (--spec-mtp-strict-qwen) with
# backend sampling, n_max 16, p_min 0.60 (see the model card and the
# charlie12345/ROCmFPX ROCMI4 runbook).
#
# Tunables come from frank-default-large.env in this directory unless
# FRANK_LARGE_ENV_FILE overrides that path.
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) -------------------
: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=262144}"
: "${PARALLEL:=1}"
: "${BATCH_SIZE:=512}"
: "${UBATCH_SIZE:=256}"
: "${NUM_THREADS:=16}"
: "${THREAD_BATCH:=32}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
# Embedded-MTP (qwen35 NextN) qualified profile. The MTP head lives in the main
# GGUF, so no standalone draft file is referenced; the draft runs on ROCm0 with all layers.
: "${MTP_N_MAX:=16}"
: "${MTP_N_MIN:=0}"
: "${MTP_P_MIN:=0.60}"
: "${SPEC_MTP_STRICT_QWEN:=on}"
: "${MTP_BACKEND_SAMPLING:=on}"
: "${SPEC_DRAFT_NGL:=all}"
: "${TEMPERATURE:=1.0}"
: "${TOP_K:=20}"
: "${TOP_P:=0.95}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${CHAT_TEMPLATE_KWARGS:={}}"
: "${VERBOSITY:=4}"
# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
: "${GGML_HIP_ENABLE_UNIFIED_MEMORY:=1}"

MODEL="$MODEL_DIR/$MODEL_FILE"
MMPROJ="$MODEL_DIR/$MMPROJ_FILE"

# Optional vision projector: load it only if the file exists.
MMPROJ_ARGS=()
if [[ -f "$MMPROJ" ]]; then
    MMPROJ_ARGS=(--mmproj "$MMPROJ")
fi

for f in "$MODEL" "$CHAT_TEMPLATE_FILE"; do
    if [[ ! -f "$f" ]]; then
        echo "missing required file: $f" >&2
        exit 1
    fi
done
if [[ ! -x "$LLAMA_BIN" ]]; then
    echo "missing llama-server binary: $LLAMA_BIN" >&2
    exit 1
fi

# Any leftover PromptForge env lanes from the previous (kingjones/v3) runtime
# must stay off; this slot now runs the plain strict-MTP draft-mtp path.
unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true

# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
export HSA_OVERRIDE_GFX_VERSION
export GGML_HIP_ENABLE_UNIFIED_MEMORY

exec "$LLAMA_BIN" \
    --model "$MODEL" \
    "${MMPROJ_ARGS[@]}" \
    --chat-template-file "$CHAT_TEMPLATE_FILE" \
    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
    --alias "$ALIAS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    -dev ROCm0 \
    -ngl 999 \
    -np "$PARALLEL" \
    -t "$NUM_THREADS" \
    -tb "$THREAD_BATCH" \
    -c "$CTX_SIZE" \
    -b "$BATCH_SIZE" \
    -ub "$UBATCH_SIZE" \
    -fa on \
    -ctk "$CACHE_TYPE_K" \
    -ctv "$CACHE_TYPE_V" \
    -ctxcp "$CTX_CHECKPOINTS" \
    --cache-ram "$CACHE_RAM" \
    --cache-prompt \
    --metrics \
    --no-mmap \
    --spec-type draft-mtp \
    ${SPEC_MTP_STRICT_QWEN:+--spec-mtp-strict-qwen} \
    --spec-draft-device ROCm0 \
    --spec-draft-ngl "$SPEC_DRAFT_NGL" \
    --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" \
    ${MTP_BACKEND_SAMPLING:+--spec-draft-backend-sampling} \
    --temp "$TEMPERATURE" \
    --top-k "$TOP_K" \
    --top-p "$TOP_P" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1 \
    -lv "$VERBOSITY"