saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-24 19:43:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix quantization of EmbeddingLayerNorm (#5321)

Browse source
This commit is contained in:
Yufeng Li 2020-09-29 01:00:47 -07:00 committed by Tianlei Wu
parent 7495dc167a
commit e8b9aa1f29
1 changed files with 2 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
onnxruntime/python/tools/quantization/operators/embed_layernorm.py
View file

@ -17,6 +17,5 @@ class EmbedLayerNormalizationQuant(QuantOperatorBase):
(quantized_input_names, zero_point_names, scale_names, nodes) = \
self.quantizer.quantize_inputs(node, [2, 3, 4])
nodes.append(node)
self.quantizer.new_nodes += nodes
super().quantize()
self.quantizer.new_nodes += nodes