Junxian Ye

Some suggestions for NNI quantizer to improve support for pytorch DataParallel API

5

**Describe the issue**: It seems that NNI QAT_Quantizer doesn't support PyTorch `DataParallel` correctly, there are some suggestions for NNI to support `DataParallel` API. ## 1. Assign buffer variables with the...

interp op attributes error when converting onnx resize op.

1

# 错误描述 将onnx resize op转换成tengine interp op之后tengine interp op attributes数值不正确。 待转换的onnx模型：  转换后的tengine interp op attributes：  可以发现转换后的tengine interp op的`output_width`与`width_scale`均出现错误。预期的`output_width`是20，而预期的`width_scale`是2。 # 环境 ``` python == 3.8.12 pytorch == 1.10.0 tengine:...

Does Lingvo distributed training support RDMA?

1

Does Lingvo distributed training support RDMA? If support, how can I setup ib support?

No handlers found: "aten::zeros" and "aten::lstm" Skipped.

4

hope to support "aten::zeros" and "aten::lstm" ops, thanks!

How does torchstat compute total memory?

2

How does torchstat compute total memory for a model? For example, I use torchstat to analyze mobilenet and get the following results: ``` Total params: 4,231,976 -------------------------------------- Total memory: 38.48MB...

If my target is to get a full quantization model, does it necessary to do weight quantization reconstruction before full quantization reconstruction as the `main_imagenet.py` shown? Can I skip weight...