Shaoyu Yang

This PR is used to fix issue #281 which is a simple comment error

There seems to be a minor bug where `max_seq_length` should be of type `int`, not `str` https://github.com/thunlp/OpenPrompt/blob/f6fb080ef755c37c01b7959e7560d007049510e8/openprompt/pipeline_base.py#LL51C20-L51C20

Instruction of TVM COV

1

Hi, Jiawei @ganler . I'm sorry to bother you due to your busy schedule. I have some difficulty in collecting `branch coverage of TVM`. I followed your instructions for [Torch...

[Shape Inference] Robustness of `ConstantOfShape` operator

2

# Bug Report ## Description The following model is a `ConstantOfShape` op with a **constant input [-10]**. Of course, ONNX does not allow ConstantOfShape input to be negative ([https://onnx.ai/onnx/operators/onnx__ConstantOfShape.html#inputs](https://onnx.ai/onnx/operators/onnx__ConstantOfShape.html#inputs)). However,...

[Bug] Graph optimization model compilation error involving `Pad` operator

5

I am trying to compile an ONNX (graph below) model using TVM.  Of course, this is a complicated graph, but we can simplify it as below.  These two...

[CI] [doc] fix the dead link of resnet and mobilenet

4

Here are some dead links of resnet in the TVM doc. one of these dead links has been caught in #17017 and a PR is submitted #17015 This PR fixes...

#### Description Here is a single op: `Cast`  In TVM, when it accepts **NaN** value, it outputs **False**. However, in `PyTorch`, it outputs **True**. In Pytorch and ONNX, `Cast`...

#### Description This torch model has only two ops: `ReflectionPad3d` and `squeeze` Firstly, I try to export the ``torch model`` to ``onnx model``. Then I get the below. ...

如题

### Model introduction the model is created by DeepSeek team. ### Model URL https://huggingface.co/deepseek-ai/DeepSeek-V2.5 ### Additional information (Optional) _No response_ ### Decontamination As they did in Deepseek-v2 ### Author No...