hahaha

if it is causal, it should not use "gLN". But there‘s no constraint in your code. And cLN should calculate the cumulative mean & var over time steps.

AssertionError: Per-tensor support only currently

1

I convert the tflite model to int8 by tensorflow official doc, but it raises this error when i convert it to onnx.

The input order of concatenate layer is changed, when use quantize_model interface.

1

use quantize_model interface:  original convert interface: 

`2023-12-18 17:40:54.489013950 [E:onnxruntime:, sequential_executor.cc:494 ExecuteKernel] Non-zero status code returned while running QLinearMatMul node. Name:'/model/out_layer/out_layer/OutLinear/MatMul' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/quantization/quantize_linear_matmul.cc:55 virtual onnxruntime::common::Status onnxruntime::QLinearMatMul::Compute(onnxruntime::OpKernelContext*) const IsBQuantParamSupported(b_offset->Shape(), b ? b->Shape() : b_shape_) was false. QLinearMatmul...