diff --git a/src/nvfp4_megamoe_kernel/nvfp4_mega_moe.py b/src/nvfp4_megamoe_kernel/nvfp4_mega_moe.py
index d4b2fd67..bf021ff1 100644
--- a/src/nvfp4_megamoe_kernel/nvfp4_mega_moe.py
+++ b/src/nvfp4_megamoe_kernel/nvfp4_mega_moe.py
@@ -164,15 +164,14 @@ def nvfp4_mega_moe_l2(
     x_sf,         # (num_slots, sf_k_groups) float8_e4m3fn
     l2_weights,   # (E_per_rank, INTER//2, HIDDEN) int8, column-major for CUTLASS
     l2_scales,    # (E_per_rank, sf_k_groups, HIDDEN) float8_e4m3fn, column-major — or prepacked
-    topk_ids,     # (num_tokens, NUM_TOPK) int32 — local expert IDs (for slot mapping)
+    slot_expert_ids,  # (num_slots,) int32 — per-slot local expert IDs (from L1 routing)
     slot_token,   # (num_slots,) int64 — token index per slot (from L1)
     alpha=1.0,    # fp32 scalar from stage_activation global scale
     sfb_prepacked=False,  # True if l2_scales is prepacked CUTLASS layout
 ):
     """L2 GEMM: down_proj — slot-based, no routing weights.
 
-    Reuses the same slot mapping from L1 (same slot_token indices).
-    topk_ids is passed to rebuild the slot→expert mapping.
+    Reuses the same slot mapping from L1 (same slot_token and slot_expert_ids).
     """
     K_half = x_fp4.shape[1]
     K = K_half * 2
@@ -187,11 +186,7 @@ def nvfp4_mega_moe_l2(
     else:
         w_sf_fp8 = l2_scales  # already prepacked
 
-    # Build 1D per-slot expert IDs (same slot ordering as L1)
-    num_experts = l2_weights.shape[0]
-    local_mask = (topk_ids >= 0) & (topk_ids < num_experts)
-    _, slot_k = local_mask.nonzero(as_tuple=True)
-    slot_expert_ids = topk_ids[slot_token, slot_k]  # (num_slots,)
+    # slot_expert_ids passed directly from L1 routing — no rebuild needed
 
     slot_out, _ = cutlass_grouped_nvfp4_gemm(
         x_fp4, x_sf_fp8,
@@ -405,7 +400,7 @@ def nvfp4_mega_moe_full(
     # Step 5: L2 GEMM — slot-based, no routing weights, prepacked SFB
     l2_slots = nvfp4_mega_moe_l2(
         l1_fp4, l1_sf_out, l2_w, l2_sf_prepacked,
-        topk_ids_local, slot_token,
+        slot_expert_local, slot_token,
         alpha=l2_alpha,
         sfb_prepacked=True,
     )  # (num_slots, HIDDEN) bfloat16