Files
AI-Profile-Router/experiments/qwen38-20260907-ab/run-benchmark.sh
T

25 lines
800 B
Bash
Executable File

#!/usr/bin/env bash
set -Eeuo pipefail
LABEL=${1:-}
CONTEXT=${2:-160000}
[[ -n $LABEL && $LABEL =~ ^[a-zA-Z0-9._-]+$ ]] || {
echo "Usage: $0 SAFE_LABEL [CONTEXT]" >&2
exit 2
}
[[ $CONTEXT =~ ^[0-9]+$ ]] || {
echo "CONTEXT must be an integer" >&2
exit 2
}
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REFERENCE_DIR="$SCRIPT_DIR/../dirk-qwen38"
RESULT_DIR=${RESULT_DIR:-/data/benchmarks/qwen38-ab-20260907}
TASKS=${TASKS:-/opt/mike-ai/stack/dev/QWEN38-FINAL-ACCEPTANCE-v1.json}
curl -fsS --max-time 3 http://127.0.0.1:5005/health >/dev/null
python3 "$REFERENCE_DIR/bench-case.py" "$LABEL" "$CONTEXT" \
--base http://127.0.0.1:5005 --output "$RESULT_DIR"
python3 "$REFERENCE_DIR/quality-ab.py" "$LABEL" \
--base http://127.0.0.1:5005 --tasks "$TASKS" --output "$RESULT_DIR"