Production-realistic baseline: APC 67.5%, TPOT +139% from interference

Updated methodology:
- Window+thin sampling preserves cross-session sharing (48% vs 16%)
- --max-single-turn-ratio 0.3 boosts multi-turn to 70%
- --window-seconds 600 for 10-min contiguous window
- Trace-driven replay (no session limit, no time compression)
- Daily config: --requests 850 (~13 min, APC~76%)

Key result: TPOT p90=0.175s (vs 0.073s in legacy 1-req/GPU setup),
confirming prefill-decode interference is real at production concurrency.
APC 67.5% (vs 44%) from better KV reuse preservation.

Also fixed KV reuse breakdown: 62% intra-session / 38% cross-session
(was incorrectly reported as 91% / 9%).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/bench.sh

@@ -21,7 +21,7 @@ VENV="${VENV_PATH:-$PROJECT_DIR/.venv/bin}"
 PYTHON="$VENV/python"
 VLLM="$VENV/vllm"
 MODEL="${MODEL_PATH:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
-TRACE="$PROJECT_DIR/traces/sampled_1000req_seed42.jsonl"
+TRACE="${TRACE:-$PROJECT_DIR/traces/sampled_1000req_seed42.jsonl}"
 
 # Defaults
 TAG=""
@@ -44,6 +44,7 @@ while [[ $# -gt 0 ]]; do
         --policy) POLICY="$2"; shift 2 ;;
         --instances) N_INSTANCES="$2"; shift 2 ;;
         --requests) REQUESTS="$2"; shift 2 ;;
+        --trace) TRACE="$2"; shift 2 ;;
         --heavy-threshold) HEAVY_THRESHOLD="$2"; shift 2 ;;
         --no-offload) NO_OFFLOAD=true; shift ;;
         --overload-factor) OVERLOAD_FACTOR_ARG="$2"; shift 2 ;;