#!/usr/bin/env bash
# Brain-Config-Matrix (Referenz vom 02.07.2026): misst Qwen3.6 in mehreren Betriebsarten
# (MTP n-max / ohne Spec / KV-Quant) auf separatem Port. Für künftige Re-Benchmarks nach
# Engine-Updates oder bei neuen Hirn-Kandidaten. Ergebnis-Referenz (02.07., Vulkan, b9843):
#   mtp3 78,6 t/s · mtp4 63,7 · ohne Spec 62,4 · mtp3+KVq8 78,6 (=gratis) · nospec+KVq8 62,1
set -u
MODEL="${BRAIN_GGUF:-/srv/models/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf}"
BIN="${BENCH_BIN:-/opt/llamacpp-vulkan/llama-server}"
PORT="${BENCH_PORT:-5899}"
BASE="-c 65536 -ngl 999 -fa on --no-mmap --jinja --parallel 1"

run() {  # $1=name  $2=extra-flags
  echo "=== $1 ==="
  $BIN -m "$MODEL" --host 127.0.0.1 --port "$PORT" $BASE $2 >/tmp/brain-bench-server.log 2>&1 &
  local PID=$!
  for i in $(seq 1 120); do
    curl -s --max-time 2 "http://127.0.0.1:$PORT/health" | grep -q ok && break
    sleep 2
    kill -0 $PID 2>/dev/null || { echo "  LOAD-CRASH"; tail -2 /tmp/brain-bench-server.log; return; }
  done
  for r in 0 1 2; do
    curl -s --max-time 300 -X POST "http://127.0.0.1:$PORT/completion" -H "Content-Type: application/json" \
      -d '{"prompt":"Erklaere in drei kurzen Saetzen, was ein Mixture-of-Experts-Modell ist.","n_predict":150,"temperature":0}' \
      > /tmp/brain-bench-probe.json
    [ "$r" = "0" ] && continue   # Warmlauf verwerfen
    python3 - <<'PY'
import json
t = json.load(open("/tmp/brain-bench-probe.json")).get("timings", {})
print(f"  tg={t.get('predicted_per_second',0):.1f} t/s"
      + (f" · draft {t.get('draft_n_accepted')}/{t.get('draft_n')}" if t.get('draft_n') else ""))
PY
  done
  kill $PID 2>/dev/null; wait $PID 2>/dev/null; sleep 3
}

run "mtp3 (live-Config)" "--spec-type draft-mtp --spec-draft-n-max 3 -ctk q8_0 -ctv q8_0"
run "mtp4"               "--spec-type draft-mtp --spec-draft-n-max 4 -ctk q8_0 -ctv q8_0"
run "ohne Spec"          "-ctk q8_0 -ctv q8_0"
run "mtp3 KV-f16"        "--spec-type draft-mtp --spec-draft-n-max 3"
echo "BENCH_DONE"