ziyanxzy

onnx_tools support DIT model?

2

You need to provide a way to get your model. You can share the model's link or some scripts to create your model. the Dit model below： https://github.com/facebookresearch/DiT I can...

[Bad Case]: how can i use model.forward to inference model?

1

### Description / 描述 i want to use model(data) to inference model instead of model.chat(input) to inference. how can i prepared the data?? ### Case Explaination / 案例解释 i can...

[Bug]: predictor compile on gpu failed

3

### OpenVINO Version 2024.4.0-16311-2c8fd1e6e97 ### Operating System Windows System ### Device used for inference GPU ### Framework None ### Model used paraformer (predictor) ### Issue description ov_predictor=ov.compile_model("predictor_static.xml","CPU") predictor_outs=ov_predictor(example_inputs) [predictor_static.zip](https://github.com/user-attachments/files/16758697/predictor_static.zip) CPU...

run onnxruntime-directml failed due to ops

1

### Describe the issue Traceback (most recent call last): File "test-paraformer-onnx.py", line 133, in main() File "test-paraformer-onnx.py", line 119, in main outputs = sess.run(output_names, input_feed=inputs) File "C:\Users\LNL\miniforge3\envs\para_3.8\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 220, in...

ConvNode groupsize=512

4

when i use this onnx_tools to profiler https://hf-mirror.com/csukuangfj/paraformer-onnxruntime-python-example. i find that this model convnode group =512,  but,  how can i use the tools in this case？

when i use debug （pdb） how to debug??

[Feature] build kernel vsa st on windows 4090s

4

### Motivation how can i build vsa kernel on windows and run pipeline on 4090? ### Related resources _No response_