#!/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 gufo (gufo-org/gufo) — the inference
# engine built specifically for this hardware.
#
# Runtime: /home/dank/GitPackages/gufo-v0.1.1/bin/gufo, built from source
# against the host ROCm by scripts/build-gufo.sh. It replaces the stock
# llama.cpp prebuilt (unsloth b11030) that served this endpoint from
# 2026-09-21; payload, port and alias are unchanged, so no client moved.
#
# Shape: one session, full 262144 context (the model's native window). The
# 27B dense weights (29.30 GiB) + the DFlash2 drafter (1.07 GiB) + KV +
# compute buffers fit the iGPU's GTT aperture (~114 GiB); gufo's own
# Q8/AR table measures 50.58 GiB peak at this context capacity.
#
# Spec method: DFlash2 (a block-diffusion drafter), gufo's adaptive block
# policy, capped at DRAFT_TOKENS proposals per step. The drafter is the
# z-lab Qwen3.8-27B-DFlash2-Q4_K_M and it has a sliding window of 2048
# (small draft KV).
#
# Sampling: greedy (--temperature 0). That is what this endpoint has always
# served, and it keeps the swap to a pure runtime change; gufo's per-model
# recommendation for Qwen3.8 thinking is sampled (1.0 / 0.95 / top-k 20) and
# is a separate decision.
#
# Template: gufo compiles the official Qwen Jinja into the binary and takes
# no --chat-template-file. Its Qwen27B default is thinking ON at xhigh effort
# with prior reasoning preserved, which is the contract the fleet already
# depends on, so --think auto + --preserve-thinking on is spelled out here
# rather than left implicit.
#
# Text-only: gufo auto-discovers a mmproj beside the model and this payload
# has none, so the endpoint stays text-only.
#
# 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) ------------------
: "${RUNTIME_DIR:=/home/dank/GitPackages/gufo-v0.1.1}"
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL}"
: "${ALIAS:=frank-large}"
: "${HOST:=0.0.0.0}"
: "${PORT:=7770}"
: "${CONTEXT_SIZE:=262144}"
: "${SESSIONS:=1}"
: "${DRAFT_TOKENS:=7}"
: "${DRAFT_POLICY:=adaptive}"

GUFO_BIN="$RUNTIME_DIR/bin/gufo"
MODEL_FILE="$MODEL_DIR/Qwen3.8-27B-UD-Q8_K_XL.gguf"
DRAFTER_FILE="$MODEL_DIR/Qwen3.8-27B-DFlash2-Q4_K_M.gguf"

if [[ ! -x "$GUFO_BIN" ]]; then
    echo "runtime not found at $GUFO_BIN" >&2
    echo "frank-large: build it: bash scripts/build-gufo.sh" >&2
    exit 1
fi
for f in "$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 -------------------------------------------------------------------
# gufo links against the host ROCm through its RPATH (/opt/rocm ->
# /etc/alternatives/rocm), so no LD_LIBRARY_PATH is needed. The device is
# already gfx1151 — `gufo diagnose` reports it natively — so no
# HSA_OVERRIDE_GFX_VERSION either; the override existed for the prebuilt
# llama.cpp runtime and can only misreport the arch here.
export HIP_VISIBLE_DEVICES=0

# --- the serve command ---------------------------------------------------
# Server options precede the subcommand, model options follow it.
exec "$GUFO_BIN" serve \
    --host "$HOST" \
    --port "$PORT" \
    --sessions "$SESSIONS" \
    llm \
    --model "$MODEL_FILE" \
    --served-model-name "$ALIAS" \
    --context "$CONTEXT_SIZE" \
    --speculative dflash2 \
    --dflash-model "$DRAFTER_FILE" \
    --draft-tokens "$DRAFT_TOKENS" \
    --draft-policy "$DRAFT_POLICY" \
    --temperature 0 \
    --think auto \
    --preserve-thinking on