Trace runner (run_v3_trace.sh) + concurrent mb7 correctness test

microbench/connector_tax/layerwise/run_mb7.sh

@@ -23,6 +23,7 @@ GPUS=(${GPUS:-0 1})
 SIZES="${SIZES:-8192,16384,32768}"
 REPEATS="${REPEATS:-3}"
 BG_LOAD="${BG_LOAD:-0}"
+CONCURRENT="${CONCURRENT:-1}"
 MAX_BATCHED="${MAX_BATCHED:-40960}"   # >= max prompt => no chunked prefill
 DATE="$(date +%Y%m%d_%H%M)"
 OUTDIR="${OUTDIR:-$PROJ_DIR/outputs/mb7_${MODE}_${DATE}}"
@@ -102,7 +103,7 @@ echo "[run] mb7 --mode $MODE"
     --src-port "${PORTS[0]}" --dst-port "${PORTS[1]}" \
     --src-bp "${BPS[0]}" --dst-bp "${BPS[1]}" \
     --sizes "$SIZES" --repeats "$REPEATS" --bg-load "$BG_LOAD" \
-    --out "$OUTDIR/mb7_result.json" \
+    --concurrent "$CONCURRENT" --out "$OUTDIR/mb7_result.json" \
     2>&1 | tee "$OUTDIR/mb7_run.txt"
 
 echo "[done] $OUTDIR"