diff --git a/docs/LLM/ciru-activefpx-promptforge.md b/docs/LLM/ciru-activefpx-promptforge.md
index ecded44..be9323f 100644
--- a/docs/LLM/ciru-activefpx-promptforge.md
+++ b/docs/LLM/ciru-activefpx-promptforge.md
@@ -253,7 +253,7 @@ ngram draft costs its own forward pass / occupancy without adding enough
 accepted tokens on top of MTP. Baseline (no ngram) remains the production
 config (`--spec-type draft-mtp` only). Keep ngram-mod off.
 
-The harness lives at [scripts/bench-spec-stack.sh](../../scripts/bench-spec-stack.sh);
+The historical harness was moved to `.AGENTTRASH/bench-scripts-20260901/` and is retained for audit only.
 it boots the v3 stack on a scratch port and reads authoritative
 `print_timing` lines. It requires the production service to be stopped.
 
diff --git a/docs/LLM/eemin-rocmi4-mtp.md b/docs/LLM/eemin-rocmi4-mtp.md
index 16ae9dc..653bac2 100644
--- a/docs/LLM/eemin-rocmi4-mtp.md
+++ b/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