Lucas
Lucas
Traceback (most recent call last): File "D:\code\AI\BigDL\python\nano\client-application\StableDiffusion\stable_diffusion\converter.py", line 66, in convert nano_pipe.convert_pipeline(accelerator=accelerator, device=device, precision=precision, ipex=ipex, cache=True, low_memory=low_memory, cache_dir=cache_dir) File "C:\Users\lustrew\miniconda3\envs\bigdl-sd\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "D:\code\AI\BigDL\python\nano\client-application\StableDiffusion\stable_diffusion\pipelines\nano_stable_diffusion.py", line...
### 可改进的内容 latexmk编译,博士论文开题报告模板不对,标题里面没有开题报告 具体模板如下: [开题报告模板.docx](https://github.com/TheNetAdmin/zjuthesis/files/11608001/default.docx) ### 代码与步骤 _No response_ ### 预期结果 _No response_
Cannot work with librosa 0.8.0 as specified by `setup.py`. ``` from . import datasets, models, text File "/home/mandarin/mtts/models/__init__.py", line 1, in from . import decoder, encoder, postnet, vocoder File "/home/mandarin/mtts/models/vocoder/__init__.py",...
1. put `b + p` inside MMM hardware 2. support smaller bit-length to run in hardware with bigger bit-length
Current cross-lane design require more documents, shall we have a review about it? I suggest we spend about 2-3 meetings to discuss about it, including: - relative files, hardware architecture...