#!/usr/bin/env bash
# Serve unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL as frank-large on
# Dankclaw's Strix Halo iGPU (gfx1151), using stock llama.cpp
# (mainline, the unsloth b11030 prebuilt).
#
# Runtime: /home/dank/GitPackages/unsloth-llama-b11030/llama-server
# (mainline, ROCm gfx1151 prebuilt). The build supports the qwen3_5
# architecture and the DFlash2 drafter (llama_model_qwen35,
# llama_model_dflash, common_speculative_impl_draft_dflash).
#
# Shape: one stream, full 262144 context (the model's native window), all
# layers on the iGPU (--n-gpu-layers 999). The 27B dense model (31.46 GiB GGUF) + the
# DFlash2 drafter (1.14 GiB) + q8_0 KV (~8.6 GiB) + compute buffers fits the
# iGPU's GTT aperture (~114 GiB).
#
# Spec method: DFlash2 (a block-diffusion drafter) at depth 4. The drafter
# has a sliding window of 2048 (small draft KV, ~40 MiB).
#
# KV: q8_0 quantized (--cache-type-k q8_0 --cache-type-v q8_0). The unsloth b11030
# build does not support fp8 KV (allowed: f32/f16/bf16/q8_0/q4_0/q4_1/iq4_nl/q5_0/
# q5_1); q8_0 is the highest-precision 8-bit option and preserves the ~8 GiB footprint.
#
# Text-only (no mmproj) — matching the prior frank-large.
#
# The Qwen3.8 family template keeps prior thinking blocks across turns when
# preserve_thinking is set; pass --jinja and the kwarg so multi-turn agents
# do not lose the trail. The template gates reasoning_effort to {xhigh,
# medium, low} — the harness folds its levels onto that set in models.yml
# (reasoningEffortMap).
#
# Tunables come from frank-large.env unless FRANK_LARGE_ENV_FILE overrides
# it; anything not set there falls through to the defaults below.
set -euo pipefail

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

# --- defaults (used when the env file does not set them) ------------------
: "${RUNTIME_DIR:=/home/dank/GitPackages/unsloth-llama-b11030}"
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL}"
: "${HOST:=0.0.0.0}"
: "${PORT:=7770}"
: "${CONTEXT_SIZE:=262144}"
: "${PARALLEL_SLOTS:=1}"
: "${SPEC_DRAFT_N_MAX:=4}"
: "${CACHE_RAM:=8192}"
TEMPLATE_FILE="${TEMPLATE_FILE:-$SCRIPT_DIR/../dankserver/frank-medium/qwen-sharp-v22.4.0.jinja}"

SERVER_BIN="$RUNTIME_DIR/llama-server"
MODEL_FILE="$MODEL_DIR/Qwen3.8-27B-UD-Q8_K_XL.gguf"
DRAFTER_FILE="$MODEL_DIR/Qwen3.8-27B-DFlash2-Q4_K_M.gguf"

if [[ ! -x "$SERVER_BIN" ]]; then
    echo "runtime not found at $SERVER_BIN" >&2
    exit 1
fi
for f in "$MODEL_FILE" "$DRAFTER_FILE"; do
    if [[ ! -f "$f" ]]; then
        echo "missing asset $f (run scripts/download-frank-large.sh)" >&2
        exit 1
    fi
done

# --- env (the unsloth build's ROCm setup) --------------------------------
export HIP_VISIBLE_DEVICES=0
export HSA_OVERRIDE_GFX_VERSION=11.5.1
export LD_LIBRARY_PATH="/opt/rocm/lib:/opt/rocm/llvm/lib:${LD_LIBRARY_PATH:-}"

# --- the serve command ---------------------------------------------------
ARGS=(
    --host "$HOST"
    --port "$PORT"
    --model "$MODEL_FILE"
    --alias frank-large
    --ctx-size "$CONTEXT_SIZE"
    --parallel "$PARALLEL_SLOTS"
    --n-gpu-layers 999
    --jinja
    --chat-template-file "$TEMPLATE_FILE"
    --chat-template-kwargs '{"preserve_thinking":true}'
    --cache-type-k q8_0
    --cache-type-v q8_0
    --cache-ram "$CACHE_RAM"
    # DFlash2 spec decode (a block-diffusion drafter)
    --spec-type draft-dflash
    --model-draft "$DRAFTER_FILE"
    --spec-draft-n-max "$SPEC_DRAFT_N_MAX"
    --spec-draft-n-min 0
    --spec-draft-device ROCm0
    # Greedy sampling (the DFlash2 drafter needs greedy verification)
    --temp 0
    --top-p 1.0
    --top-k 0
    --min-p 0.0
    # Reasoning (thoughts land in reasoning_content)
    --reasoning auto
    --reasoning-format deepseek
    --reasoning-budget -1
)

exec "$SERVER_BIN" "${ARGS[@]}"