Open chenfeiyue-cfy opened 1 month ago
Do you have a model where this causes an issue?
Sure, the model is downloaded from onnx model zoo:(https://github.com/onnx/models/blob/main/validated/vision/classification/densenet-121/model/densenet-12-int8.onnx). The unit test is from path onnxruntime/onnxruntime/test/contrib_ops/qlinear_concat_test.cc(https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/test/contrib_ops/qlinear_concat_test.cc)
I don't think the lack of support makes a difference in this case.
QLinearConcat is an internal operator, so we would expect it to be handled by our internal execution providers. In that scenario, the fact that the zp/scale values aren't nicely provided by the NodeUnit doesn't change anything as nothing (AFAIK) is trying to read the zp and scale from the NodeUnit as we have static kernels for CPU/CUDA/DML execution providers to handle QLinearConcat.
Really for the model to be in the ONNX repo it should be in QDQ format (DequantizeLinear on each input with a Concat node and a QuantizeLinear on the output) instead of having been saved using internal onnxruntime operators. With that model format any execution provider could convert the set of nodes into a quantized concat operation, and it would want the zp/scale for the inputs to be conveniently available via the NodeUnit. That's a different NodeUnit constructor though and not the path with the TODO comment.
Sure it is not an error occured, but in the node_unit.cc file, I saw QLinearMatMul and QLinearConv opshave been handled like that .QDQMatmul/QDQConv have made node_arg and quant_param binded together with one single input for node_unitI made this request because our execution provider treats quantization operations and normal operations equally.If QLinearConcat could be easier to get input like QLinearConv it will make our provider work more efficiently.
I have added an item to the backlog to look at adding the quantization info to a NodeUnit for the QLinearX operators. No guarantee when we'll get to it though.
Describe the issue
May I ask when will onnxruntime support for setting inputs for the QLinearConcat operator in node unit structure be available? I saw a ‘todo’ note in the code, but there has been no progress for the past two years.”![企业微信截图_1716798582784](https://github.com/microsoft/onnxruntime/assets/69809761/34e1a329-372f-437f-b3c4-717ab85d65e6)
To reproduce
File path:node_unit.cc. I found that onnxruntime does not handle the inputs of the QLinearConcat's node_unit in the same way as it does with other QLinear operators, that is, by binding each actual input with its quantization information into a single input.
Urgency
No response
Platform
Linux
OS Version
Ubuntu 22.04.2 LTS
ONNX Runtime Installation
Built from Source
ONNX Runtime Version or Commit ID
main
ONNX Runtime API
C++
Architecture
X86
Execution Provider
Default CPU, NNAPI, Other / Unknown
Execution Provider Library Version
No response