Gooddz1 issues

Results 8 issues of


                                            Gooddz1

getPluginCreator could not find plugin ScatterND version 1

你好，在转换trt的时候，[TensorRT] ERROR: INVALID_ARGUMENT: getPluginCreator could not find plugin ScatterND version 1 是因为我用的tensorrt是7的原因吗？那么，可以帮忙在使用tensorrt7的工程中，添加ScatterND 的插件吗？期待更新 https://github.com/NVIDIA/TensorRT/tree/release/8.0/plugin/scatterPlugin

Comparison exception: The values for attribute 'shape' do not match: torch.Size([]) != torch.Size([1, 8400]).

使用nni对yolov8进行剪枝，报了如下错误 Comparison exception: The values for attribute 'shape' do not match: torch.Size([]) != torch.Size([1, 8400]).

How do I need to modify the configuration file to use Anytool's pruned version of the model when downloading it?

How do I need to modify the configuration file to use Anytool's pruned version of the model when downloading it? Download link for Anytool pruning model: https://modelscope.cn/models/bdsqlsz/AnyDoor-Pruned/feedback

使用aarch64-linux-gnu-g++编译时，在编译ggml会报错

报了如下错误 ``` aarch64-linux-gnu-gcc: 错误： unrecognized command line option ‘-mavx’ aarch64-linux-gnu-gcc: 错误： unrecognized command line option ‘-mavx2’ aarch64-linux-gnu-gcc: 错误： unrecognized command line option ‘-mfma’ aarch64-linux-gnu-gcc: 错误： unrecognized command line option ‘-mf16c’...

有打算支持qwen吗

qwen这个速度挺快的，有打算支持qwen吗？

whisper在rk3588中推理的RTF为1.3左右，和介绍的RTF0.392不太一样

-- init_whisper_decoder_model use: 221.897003 ms -- read_mel_filters & read_vocab & read_audio use: 11.515000 ms -- inference_whisper_model use: 7662.529785 ms Whisper result: Mr. Quilter is the apostle of the middle classes...

Can not find the layer type: pnnx.Attribute

利用kuiperinfer实现yolov8推理，出现”Can not find the layer type: pnnx.Attribute “的错误