#!/usr/bin/env bash
# Serve unsloth/Qwen3.8-27B-UD-Q8_K_XL as frank-default-large with a
# z-lab DFlash2 drafter (Qwen3.8-27B-DFlash2-Q4_K_M) on the Vulkan backend.
#
# Runtime: upstream llama.cpp PR #27342 (DFlash2 support) built with
# GGML_VULKAN=ON for the Strix Halo gfx1151 (RADV). DFlash2 selects its
# candidates through TOP_K + ARGMAX ops that the HIP backend does not
# implement, so the whole stack runs on Vulkan0.
#
# The target and the drafter share the Qwen3.8 arch. DFlash is lossless
# under strict rejection sampling. --spec-draft-n-max clamps to the drafter's
# trained block size (8).
#
# 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) -------------------
: "${LLAMA_BIN:=/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models}"
: "${MODEL_FILE:=Qwen3.8-27B-UD-Q8_K_XL.gguf}"
: "${DRAFT_FILE:=Qwen3.8-27B-DFlash2-Q4_K_M.gguf}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=52625}"
: "${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_TYPE:=draft-dflash}"
: "${SPEC_DRAFT_N_MAX:=8}"
: "${SPEC_DRAFT_N_MIN:=0}"
: "${SPEC_DRAFT_P_MIN:=0.0}"
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
: "${TEMPERATURE:=0.7}"
: "${TOP_P:=0.95}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${VERBOSITY:=4}"

MODEL="$MODEL_DIR/$MODEL_FILE"
DRAFT="$MODEL_DIR/$DRAFT_FILE"

if [[ ! -f "$MODEL" ]]; then
    echo "missing required file: $MODEL" >&2
    exit 1
fi
if [[ ! -f "$DRAFT" ]]; then
    echo "missing DFlash2 drafter: $DRAFT" >&2
    exit 1
fi
if [[ ! -x "$LLAMA_BIN" ]]; then
    echo "missing llama-server binary: $LLAMA_BIN" >&2
    exit 1
fi

exec "$LLAMA_BIN" \
    --model "$MODEL" \
    --alias "$ALIAS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    -dev Vulkan0 \
    -ngl 999 \
    -c "$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 "$CACHE_RAM" \
    --cache-prompt \
    --metrics \
    --no-mmap \
    --spec-type "$SPEC_TYPE" \
    --spec-draft-model "$DRAFT" \
    --spec-draft-device Vulkan0 \
    --spec-draft-ngl 999 \
    --spec-draft-type-k f16 \
    --spec-draft-type-v f16 \
    --spec-draft-n-max "$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-p "$TOP_P" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1 \
    -lv "$VERBOSITY"