#!/bin/bash
# Experiment C: kvcache-centric (session-aware PD)
# 1P(GPU 0-3) + 1D(GPU 4-7), TP4, mooncake TCP
# Full 39K trace from SWE-Bench 500 instances
set -euo pipefail
cd "$(dirname "$0")/.."

uv run agentic-pd-hybrid benchmark-live \
  --trace outputs/qwen35-swebench-500.jsonl \
  --output-root outputs/swebench-exps \
  --mechanism kvcache-centric \
  --policy default \
  --model-path /mnt/kzlin/workflow/pd-hybrid/simm-swe-bench/models/Qwen3.5-35B-A3B \
  --prefill-workers 1 --decode-workers 1 \
  --prefill-tp-size 4 --decode-tp-size 4 \
  --prefill-gpu-ids 0,1,2,3 --decode-gpu-ids 4,5,6,7 \
  --transfer-backend mooncake \
  --gpu-budget 8 \
  --time-scale 10 \
  --session-sample-rate 1.0 \
  --target-duration-s 100000 \
  --concurrency-limit 64 \
  --timeout-s 900 \
  --request-timeout-s 300 \
  --kvcache-admission-mode worker \
  --kvcache-seed-min-turn-id 2 \
  --kvcache-prefill-backup-policy release-after-transfer \
  --kvcache-prefill-priority-eviction