Update benchmark documentation after harness replacement

docs/LLM/eemin-rocmi4-mtp.md

@@ -142,7 +142,9 @@ Decode throughput depends on the ubatch (per-eval token batch). Run the sweep
 on 8k contexts, 512 → 4096 in steps of 512, with a fixed batch:
 
 ```
-STOPSVC=1 ./scripts/bench-ubatch-rocmi4.sh
+sudo systemctl stop frank-default-large
+./scripts/bench-ubatch.sh
+sudo systemctl start frank-default-large
 ```
 
 The script stops `frank-default-large` for a clean GPU, boots one server