diff --git a/single_shot_inference.py b/single_shot_inference.py
index 8316e94e..b9742290 100644
--- a/single_shot_inference.py
+++ b/single_shot_inference.py
@@ -685,9 +685,9 @@ def forward_attention(x_normed, w, li, cfg, rope_cos, rope_sin,
     # With: fused rmsnorm+NVFP4 quantize → QuantizedActivation → q_b.run_from_quantized
     # Saves: ~6 kernel launches per layer (rmsnorm 4+ + quantize 2 vs fused 2)
     if q_norm_w is not None:
-        from dsv4.ops.quantize import rmsnorm_quantize_nvfp4 as _rmsnorm_quantize
+        from dsv4.ops.quantize import rmsnorm_quantize_nvfp4 as _rmsnorm_quantize, dequantize_nvfp4 as _dequantize_nvfp4
         q_a_quant = _rmsnorm_quantize(q_a, q_norm_w.to(dev, torch.float32))
-        q_a = dequantize_nvfp4(q_a_quant.x_fp4, q_a_quant.x_sf, q_a_quant.gsa)
+        q_a = _dequantize_nvfp4(q_a_quant.x_fp4, q_a_quant.x_sf, q_a_quant.gsa)
     _pt('q_b_start')
     if q_norm_w is not None:
         q = prod_lin['q_b'].run_from_quantized(q_a_quant)