From 157bf3668d11ea6daea90066a8c0ff1fd24ab14b Mon Sep 17 00:00:00 2001
From: Gahow Wang <gahow.wang@gmail.com>
Date: Mon, 20 Jul 2026 18:11:33 +0800
Subject: [PATCH] fix: isolate simulator predictor cache

---
 ...run_frontier_qwen30_exact_trace_surface.py |  9 ++++-
 .../jobs_simulator_v4.toml                    | 33 +++++++++++++++++++
 .../run_simulator_group.sh                    |  5 +--
 3 files changed, 44 insertions(+), 3 deletions(-)
 create mode 100644 runs/frontier-workload-regime-taxonomy-v0/jobs_simulator_v4.toml

diff --git a/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py b/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py
index 9c869d8..57c0346 100644
--- a/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py
+++ b/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py
@@ -611,6 +611,12 @@ def main() -> None:
             command = configure_stage_batch_ledger(
                 command, enabled=args.store_stage_batch_ledger
             )
+            command.extend(
+                [
+                    "--metrics_config_cache_dir",
+                    str(args.output_root / "cache"),
+                ]
+            )
             if args.align_real_graph_runtime:
                 command.extend(
                     [
@@ -640,7 +646,7 @@ def main() -> None:
                 )
             fallback_evidence = (
                 collective_fallback_evidence(run_dir)
-                if args.cc_backend == "vidur"
+                if args.cc_backend == "vidur" and config.tp > 1
                 else []
             )
             if completed.returncode == 0 and fallback_evidence:
@@ -823,6 +829,7 @@ def main() -> None:
             "arrival": "original_trace_timestamp_and_order",
             "input_output": "exact_source_values",
             "store_stage_batch_ledger": args.store_stage_batch_ledger,
+            "predictor_cache_root": str(args.output_root / "cache"),
             "ttft_slo": "1000ms + 1000ms * input_tokens / 8000",
             "tpot_slos_ms": TPOT_SLOS_MS,
             "primary_tpot_slo_ms": 150.0,
diff --git a/runs/frontier-workload-regime-taxonomy-v0/jobs_simulator_v4.toml b/runs/frontier-workload-regime-taxonomy-v0/jobs_simulator_v4.toml
new file mode 100644
index 0000000..0ed8cd3
--- /dev/null
+++ b/runs/frontier-workload-regime-taxonomy-v0/jobs_simulator_v4.toml
@@ -0,0 +1,33 @@
+version = 1
+
+[[jobs]]
+name = "workload-regime-sim-tp1-v4-20260720"
+gpus = 1
+gpu_model = "H20"
+hosts = ["dash1"]
+command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 1 both"
+artifacts = []
+
+[[jobs]]
+name = "workload-regime-sim-tp2-v4-20260720"
+gpus = 1
+gpu_model = "H20"
+hosts = ["dash2"]
+command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 2 both"
+artifacts = []
+
+[[jobs]]
+name = "workload-regime-sim-tp4-noprefix-v4-20260720"
+gpus = 1
+gpu_model = "H20"
+hosts = ["dash3"]
+command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 false"
+artifacts = []
+
+[[jobs]]
+name = "workload-regime-sim-tp4-prefix-v4-20260720"
+gpus = 1
+gpu_model = "H20"
+hosts = ["dash4"]
+command = "bash runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh 4 true"
+artifacts = []
diff --git a/runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh b/runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh
index b2af749..6b60b19 100644
--- a/runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh
+++ b/runs/frontier-workload-regime-taxonomy-v0/run_simulator_group.sh
@@ -22,8 +22,9 @@ REPLAYSERVE_ROOT="${REPLAYSERVE_ROOT:-/home/admin/cpfs/wjh/replayserve}"
 PROFILE_ROOT="${PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/profile-v4-trace-final}"
 KERNEL_PROFILE_ROOT="${KERNEL_PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/graph-piecewise-qwen30-20260717/full/frozen-kernel-only}"
 ALLREDUCE_CSV="${ALLREDUCE_CSV:-/home/admin/cpfs/wjh/aituner/aituner-graph-piecewise-bdc357d/runs/frontier-fidelity-envelope-v1/profiles/measured-allreduce.csv}"
-CUSTOM_PYTHON_DEPS="${CUSTOM_PYTHON_DEPS:-${EXPERIMENT_ROOT}/python-deps}"
+CUSTOM_PYTHON_DEPS="${CUSTOM_PYTHON_DEPS:-${EXPERIMENT_ROOT}/python-deps-v2}"
 BASE_PYTHON_DEPS="${BASE_PYTHON_DEPS:-/home/admin/cpfs/wjh/venvs/qwen36-vllm-0.20.2/lib/python3.12/site-packages}"
+SIM_GENERATION="${SIM_GENERATION:-v4}"
 RUNNER="${CHECKOUT}/runs/frontier-fidelity-envelope-v1/run_frontier_qwen30_exact_trace_surface.py"
 
 for path in "${TRACES_ROOT}/manifest.json" "${FRONTIER_SOURCE}" \
@@ -36,7 +37,7 @@ done
 run_mode() {
   local prefix_mode="$1" output_root prefix_flag family
   local -a families traces configs command
-  output_root="${EXPERIMENT_ROOT}/sim/tp${TP}-prefix-${prefix_mode}"
+  output_root="${EXPERIMENT_ROOT}/sim-${SIM_GENERATION}/tp${TP}-prefix-${prefix_mode}"
   mkdir -p "${output_root}/provenance"
 
   if [[ "${prefix_mode}" == "true" ]]; then