From 9d4a014fadef9c7cc82fed3b99999d1848938e95 Mon Sep 17 00:00:00 2001 From: biondizzle Date: Tue, 2 Jun 2026 21:52:29 +0000 Subject: [PATCH] Fix NameError: dequantize_nvfp4 not in scope in forward_attention The B3 fused q_a_norm path used dequantize_nvfp4 but it was only imported in forward_layer, not forward_attention. Added local import. --- single_shot_inference.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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)