#!/bin/bash
# Run the interference microbenchmark sweep.
# Assumes vLLM is already running on the specified port.
#
# Usage: bash run_sweep.sh [port] [chunk_size]

set -euo pipefail

PORT=${1:-8000}
CHUNK_SIZE=${2:-8192}
REPS=${REPS:-5}
OUTPUT_DIR="results/interference"

echo "=== Interference Microbench Sweep ==="
echo "Server: http://127.0.0.1:$PORT"
echo "Chunk size: $CHUNK_SIZE"
echo "Reps: $REPS"
echo "Output: $OUTPUT_DIR"
echo ""

# Quick sanity check
curl -sf "http://127.0.0.1:$PORT/v1/models" > /dev/null || {
    echo "ERROR: vLLM not reachable on port $PORT"
    exit 1
}

cd "$(dirname "$0")"

python driver.py \
    --host 127.0.0.1 \
    --port "$PORT" \
    --chunk-size "$CHUNK_SIZE" \
    --decode-batch-sizes "0,1,2,4,6,8,12" \
    --prefill-tokens "512,1024,2048,4096,8192,16384,32768" \
    --reps "$REPS" \
    --output-dir "$OUTPUT_DIR"