#!/usr/bin/env bash
# Serve kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP (dense) as
# frank-default-large via the CIRU ROCmFPX llama.cpp runtime on Dankclaw
# (Strix Halo gfx1151).
#
# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
# qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) plus the v3 output-K8
# runtime patch (commit af0eac6), against the private TheRock ROCm 7.15 SDK
# (kept in the retired ling3-ciru venv). The model is the plain ROCmFP4
# Q6 AGENT GGUF (no PromptForge .pfs sidecars) with the standalone MTP draft
# head mtp-Qwen3.8-27B-Q4_0.gguf. The Qwen-Sharp chat template is applied at
# runtime.
#
# Spec: dense model -> native MTP draft at n_max 4 (the knee, per the model
# card). The draft head is a separate Q4_0 GGUF loaded via --model-draft.
#
# The model card requires ROCm 7.15 (not the system ROCm 7.2.4) for the
# advertised Strix Halo performance. LD_LIBRARY_PATH therefore points at the
# 7.15 SDK libraries first.
#
# 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) -------------------
: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
: "${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:=mtp-Qwen3.8-27B-Q4_0.gguf}"
: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
: "${ROCM_DEVEL:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel}"
: "${ROCM_LIB:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries}"
: "${ROCM_CORE:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=262144}"
: "${PARALLEL:=1}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=4096}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
: "${SPEC_DRAFT_N_MAX:=4}"
: "${SPEC_DRAFT_N_MIN:=0}"
: "${SPEC_DRAFT_P_MIN:=0.0}"
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
: "${TEMPERATURE:=1.0}"
: "${TOP_K:=20}"
: "${TOP_P:=0.95}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${CHAT_TEMPLATE_KWARGS:={}}"
: "${VERBOSITY:=4}"

MODEL="$MODEL_DIR/$MODEL_FILE"
MTP_DRAFT="$MODEL_DIR/$MTP_DRAFT_FILE"

# Plain dense model: no PromptForge .pfs sidecars, no Output-K8 proxy, no IU4
# lane. The v3 MTP is driven by the standalone Q4_0 draft head through the
# standard draft-mtp path. Unset any leftover PromptForge env lanes.
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

for f in "$MODEL" "$MTP_DRAFT" "$MODEL_DIR/$MMPROJ_FILE" "$CHAT_TEMPLATE_FILE"; do
    if [[ ! -f "$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

# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
export ROCM_PATH="$ROCM_DEVEL"
export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"

exec "$LLAMA_BIN" \
    --model "$MODEL" \
    --mmproj "$MODEL_DIR/$MMPROJ_FILE" \
    --chat-template-file "$CHAT_TEMPLATE_FILE" \
    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
    --alias "$ALIAS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    -dev ROCm0 \
    -ngl 999 \
    -c "$CTX_SIZE" \
    -b "$BATCH_SIZE" \
    -ub "$UBATCH_SIZE" \
    -fa on \
    -ctk "$CACHE_TYPE_K" \
    -ctv "$CACHE_TYPE_V" \
    -np "$PARALLEL" \
    -ctxcp "$CTX_CHECKPOINTS" \
    --cache-ram "$CACHE_RAM" \
    --cache-prompt \
    --metrics \
    --no-mmap \
    --spec-type draft-mtp \
    --model-draft "$MTP_DRAFT" \
    --spec-draft-device ROCm0 \
    --spec-draft-ngl 999 \
    --spec-draft-type-k f16 \
    --spec-draft-type-v f16 \
    --spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
    --spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
    --spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
    --spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
    --temp "$TEMPERATURE" \
    --top-k "$TOP_K" \
    --top-p "$TOP_P" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1 \
    -lv "$VERBOSITY"