Wang Yi
Wang Yi
> > you can continue use Python3.12, just install pytorch manually by command like `pip install torch==2.2.0+cu121`, and add param ` --skip-python-version-check` when you start sd-webui service. > > Is...
@karlbernard2 Hi, thanks for your feedback and sorry for replying so late. The `removeprefix` of class str only exists at Python >= 3.9, and your Python version is 3.8, in...
@karlbernard2 Hi, the bug is fixed in https://github.com/siliconflow/onediff/pull/856 , please pull the newest onediff and have a try :)
> 后续可以顺便支持一下cache功能 cache 有 PR 了，amp 合并就继续推进
> Related PR: https://github.com/Oneflow-Inc/oneflow/pull/9363/files#r1018792218 这个 PR 已经合了
Hi，请问您是在哪个平台上安装的 OneFlow，以及报错信息是什么呢？
> 原因是 torch 的 diagonal 操作是个 view op： > > ```python > import torch as torch_original > > print("torch test:") > inputs = torch_original.rand(3, 3) > y = inputs.diagonal(0) >...
> api docs的截图贴一下吧 贴上了，在一楼
I'm using torch==1.4.0 and python==3.7.0
Thanks for your reply! I modified my code according your suggestion. ```python3 net.load_state_dict(weight) net = net.eval().cuda() x = torch.ones([20,3,112,112]).cuda() trt_net = ttrt.torch2trt(net, [x], max_batch_size=20) trt_net_fp16 = ttrt.torch2trt(net, [x], max_batch_size=20, fp16_mode=True,...