diff --git a/deepinfer/engine/llm_engine.py b/deepinfer/engine/llm_engine.py
index acc295c..0a92acb 100644
--- a/deepinfer/engine/llm_engine.py
+++ b/deepinfer/engine/llm_engine.py
@@ -395,7 +395,10 @@ class LLMEngine:
             # Neuron: the follower claims core cp_rank of CUDA_VISIBLE_DEVICES (deepinfer/platform.py); the spawned
             # process copies this environment at start.
             # Runtime profiling (NEURON_RT_INSPECT_*) stays on the driver: 64 ranks would overwrite one output dir.
-            overrides = {"DEEPINFER_NEURON_LOCAL_RANK": str(cp_rank), "NEURON_RT_INSPECT_ENABLE": "0"}
+            # DEEPINFER_NEURON_PROFILE_RANKS (e.g. "1,63") keeps it on for those followers (each writes a pid dir).
+            overrides = {"DEEPINFER_NEURON_LOCAL_RANK": str(cp_rank)}
+            if str(cp_rank) not in os.environ.get("DEEPINFER_NEURON_PROFILE_RANKS", "").split(","):
+                overrides["NEURON_RT_INSPECT_ENABLE"] = "0"
             saved = {k: os.environ.get(k) for k in overrides}
             os.environ.update(overrides)
             try:
diff --git a/deepinfer/neuron_ops/static_moe.py b/deepinfer/neuron_ops/static_moe.py
index 0ecf76a..4201b46 100644
--- a/deepinfer/neuron_ops/static_moe.py
+++ b/deepinfer/neuron_ops/static_moe.py
@@ -38,6 +38,7 @@ _ALIGN = 16
 #: per-expert flag, blockquant.fp4_linear_2core_gated).
 _GATED_EXPERTS = os.environ.get("DEEPINFER_NEURON_GATED_EXPERTS", "1") == "1"
 _GATED_MAX_ROWS = 16
+_FLAG_FORCE = os.environ.get("DEEPINFER_NEURON_MOE_FLAG_FORCE", "")
 
 def _as_rows(t: torch.Tensor, rows: int) -> torch.Tensor:
     return t.contiguous().view(rows, -1).view(torch.uint8)
@@ -270,6 +271,8 @@ def _nki_moe_forward(
         for e in range(num_local):
             w_e = torch.where(local_idx == e, w, torch.zeros_like(w)).sum(-1)
             flag = (local_idx == e).any().to(torch.int32).reshape(1, 1) if gated else None
+            if gated and _FLAG_FORCE in ("0", "1"):  # timing diagnostic only: wrong results
+                flag = torch.full((1, 1), int(_FLAG_FORCE), dtype=torch.int32, device=x.device)
             gate_up = nki_gemm.linear_qdq_gated(x, moe.gate_up_proj_weight, e, flag) if gated else None
             if gate_up is None:
                 gate_up = nki_gemm.linear_qdq(x, moe.gate_up_proj_weight, group=e)