diff --git a/vllm/nvfp4_cutedsl.py b/vllm/nvfp4_cutedsl.py
index 196d5781..63ef48f9 100644
--- a/vllm/nvfp4_cutedsl.py
+++ b/vllm/nvfp4_cutedsl.py
@@ -242,12 +242,6 @@ class CuTeDSLMoERunner:
             sorted_token_ids = token_indices[sort_idx.cpu()].to(device)
             slot_hidden = hidden_states_sample[sorted_token_ids]
             
-            # Debug: verify slot_hidden
-            torch.cuda.synchronize()
-            _slot_check = sorted_token_ids[:8].cpu().tolist()
-            _slot_amax = slot_hidden.abs().max().item()
-            print(f"  Warmup: sorted_token_ids[:8]={_slot_check}, slot_hidden amax={_slot_amax:.6f}")
-            
             # L1: get exact gs from quantize_to_nvfp4
             _, _, l1_gs = quantize_to_nvfp4(slot_hidden)