diff --git a/microbench/fresh_setup/mb5_launch.sh b/microbench/fresh_setup/mb5_launch.sh
index 03edfd2..45bb988 100755
--- a/microbench/fresh_setup/mb5_launch.sh
+++ b/microbench/fresh_setup/mb5_launch.sh
@@ -95,16 +95,20 @@ launch_vllm() {
     local idx="$1" gpu="$2" port="$3" role="$4" bp="$5"
     local cfg="{\"kv_connector\":\"MooncakeConnector\",\"kv_role\":\"${role}\"}"
     local master=$((BASE_MASTER+idx))
-    local env_bp_arg=""
-    if [ -n "${bp}" ] && [ "${bp}" != "-" ]; then
-        env_bp_arg="VLLM_MOONCAKE_BOOTSTRAP_PORT=${bp}"
+    # Bootstrap port: always set (vllm only consumes it for producer/kv_both
+    # modes; kv_consumer mode just ignores it). Use a placeholder if the
+    # caller didn't supply one — bash one-shot env-prefix with a dynamic
+    # variable is fragile, so we always export a literal.
+    local bp_use="${bp}"
+    if [ -z "${bp_use}" ] || [ "${bp_use}" = "-" ]; then
+        bp_use="9999"
     fi
     echo "[mb5] launching idx=${idx} gpu=${gpu} port=${port} role=${role} bp=${bp:-none}"
     PYTHONHASHSEED=42 \
     MB5_LOG_DIR="${SNAPSHOT_DIR}" \
     CUDA_VISIBLE_DEVICES="${gpu}" \
     MASTER_PORT="${master}" \
-    ${env_bp_arg} \
+    VLLM_MOONCAKE_BOOTSTRAP_PORT="${bp_use}" \
     nohup vllm serve "${MODEL}" \
         --host 0.0.0.0 --port "${port}" \
         --tensor-parallel-size 1 \
diff --git a/microbench/fresh_setup/mb5_run.sh b/microbench/fresh_setup/mb5_run.sh
index 8e32d39..2efe783 100755
--- a/microbench/fresh_setup/mb5_run.sh
+++ b/microbench/fresh_setup/mb5_run.sh
@@ -71,19 +71,23 @@ run_one() {
     local t0
     t0=$(date +%s.%N)
     if ! PYTHONPATH="${FRESH_ROOT}" python -m replayer \
-            --endpoint-url "${endpoints}" \
-            --trace-path "${TRACE}" \
-            --output-path "${replay_out}" \
-            --model-name "${MODEL_NAME}" \
+            --endpoint "${endpoints}" \
+            --trace "${TRACE}" \
+            --output "${replay_out}" \
+            --model "${MODEL_NAME}" \
             ${REQUEST_LIMIT_ARG} \
             > "${OUT_ROOT}/${config}_rep${rep}_replay.log" 2>&1; then
-        local t1=$(date +%s.%N)
-        echo "[mb5-run] REPLAY FAILED after $(echo "$t1 - $t0" | bc) s; see ${OUT_ROOT}/${config}_rep${rep}_replay.log"
+        local t1
+        t1=$(date +%s.%N)
+        local wall=$(python -c "print(${t1} - ${t0})")
+        echo "[mb5-run] REPLAY FAILED after ${wall} s; see ${OUT_ROOT}/${config}_rep${rep}_replay.log"
         bash "${LAUNCH}" stop > /dev/null 2>&1 || true
         return 1
     fi
-    local t1=$(date +%s.%N)
-    local wall_clock_s=$(echo "$t1 - $t0" | bc)
+    local t1
+    t1=$(date +%s.%N)
+    local wall_clock_s
+    wall_clock_s=$(python -c "print(${t1} - ${t0})")
     echo "[mb5-run] replay done in ${wall_clock_s}s"
     echo "${wall_clock_s}" > "${rundir}/wall_clock_s.txt"