#!/bin/sh
# bench-prefill.sh — measure llama-server prefill/decode scaling on :8083
#
# Uses the server's own `timings` block (prompt_ms / predicted_ms), which is far
# more accurate than wall clock. A unique nonce is placed FIRST in every prompt to
# defeat llama.cpp prefix caching — otherwise cache_n>0 and prefill is not measured.

URL=http://127.0.0.1:8083/v1/chat/completions
OUT=/home/arduino/bench-prefill.json
UNIT="The structural sensor node recorded a nominal vibration reading during the overnight monitoring window and logged it. "

: > "$OUT"
echo "size_label,prompt_n,prompt_ms,prefill_tps,predicted_n,predicted_ms,decode_tps,cache_n,wall_s"

for reps in 12 25 50 100; do
  # build filler
  filler=""
  i=0
  while [ $i -lt $reps ]; do filler="$filler$UNIT"; i=$((i+1)); done

  nonce="$(date +%s%N)$$"
  python3 - "$nonce" "$filler" > /tmp/payload.json <<'PY'
import json,sys
nonce, filler = sys.argv[1], sys.argv[2]
content = f"[req-{nonce}] {filler}\n\nIn one short sentence, what is this text about?"
print(json.dumps({"model":"qwen","max_tokens":16,"temperature":0,
                  "messages":[{"role":"user","content":content}]}))
PY

  start=$(date +%s)
  resp=$(curl -s --max-time 1800 "$URL" -H 'Content-Type: application/json' -d @/tmp/payload.json)
  end=$(date +%s)
  wall=$((end-start))

  echo "$resp" >> "$OUT"
  echo "$resp" | jq -r --arg r "reps=$reps" --arg w "$wall" '
    [$r, .timings.prompt_n, (.timings.prompt_ms|round),
     (.timings.prompt_per_second*100|round/100),
     .timings.predicted_n, (.timings.predicted_ms|round),
     (.timings.predicted_per_second*100|round/100),
     .timings.cache_n, $w] | @csv'
done