We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent da773f1 commit cb276ccCopy full SHA for cb276cc
modelopt/onnx/quantization/graph_utils.py
@@ -866,7 +866,7 @@ def get_layer_info(
866
layers_8bit = kwargs.get("layers_8bit")
867
gather_block_size = kwargs.get("gather_block_size", DEFAULT_GATHER_BLOCK_SIZE)
868
gather_quantize_axis = kwargs.get("gather_quantize_axis", DEFAULT_GATHER_QUANTIZE_AXIS)
869
- if enable_mixed_quant:
+ if enable_mixed_quant or layers_8bit:
870
layer_info = get_layer_precision_mapping(
871
onnx_model,
872
layers_8bit,
0 commit comments