#!/usr/bin/env bash
# Unattended serial PD-ablation campaign: reuse sweep -> conc sweep.
# STRICTLY one driver at a time (the hard lesson): each inner driver brings up and
# tears down its own vLLM per config via scripts/mb5_run_gpu.sh, and the two sweeps
# run sequentially (reuse fully finishes + tears down before conc starts). We verify
# GPUs are clear between sweeps. NO set -e here: a sub-sweep nonzero must NOT skip the
# other sweep; rc is captured and reported. Detached launch writes a DONE marker.
cd /home/admin/cpfs/wjh/agentic-kv-fresh
export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
FS=microbench/fresh_setup

echo "=== CAMPAIGN START $(date) ==="

echo "=== [1/2] REUSE SWEEP (fixed real prefill delta=2048, out=256, reuse 20-95%, N=8) $(date) ==="
bash "$FS/run_reuse_fixed.sh"; rc_reuse=$?
echo "=== reuse sweep rc=$rc_reuse $(date) ==="

sleep 15
echo "--- GPU mem after reuse sweep (expect ~0 before conc) ---"
nvidia-smi --query-gpu=index,memory.used --format=csv,noheader | head -8

echo "=== [2/2] CONC SWEEP (in=32768 reuse=0.984, balanced N grid 8 16 32 48 64 96 128) $(date) ==="
NLIST="8 16 32 48 64 96 128" bash "$FS/run_conc.sh"; rc_conc=$?
echo "=== conc sweep rc=$rc_conc $(date) ==="

echo "=== CAMPAIGN DONE reuse_rc=$rc_reuse conc_rc=$rc_conc $(date) ==="