minor

realAsma · realAsma · commit f8bbfe543562 · 2025-09-23T18:01:04.000Z
diff --git a/modelopt/torch/quantization/nn/modules/tensor_quantizer.py b/modelopt/torch/quantization/nn/modules/tensor_quantizer.py
@@ -915,7 +915,6 @@ def forward(self, inputs):
                 )
                 assert block_size is not None, "block size for dynamic quantization not found."
 
-            # Collect calibration data for bias
             self.collect(inputs)
 
         if self._if_quant:

Original file line number	Diff line number	Diff line change
`@@ -915,7 +915,6 @@ def forward(self, inputs):`
`915`	`915`	`)`
`916`	`916`	`assert block_size is not None, "block size for dynamic quantization not found."`
`917`	`917`
`918`		`- # Collect calibration data for bias`
`919`	`918`	`self.collect(inputs)`
`920`	`919`
`921`	`920`	`if self._if_quant:`