-
I have a prolem with running CUDA on GPU. When I'm runnig command:
`python inference_codeformer.py --bg_upsampler realesrgan --face_upsample -w 0.7 --input_path G:\AI\CodeFormer\results\test1.jpg`
…
-
### Describe the proposed feature and its relevance to inferencing
Document how to take a random PyTorch model and make it run in Godot Engine IREE.gd
### Context or use case
1. https://githu…
-
### Describe the issue
I converted a xlnet model to onnx, and the model is 3 times slower compared to pytorch in centos 7. I tried add_session_config_entry("session.set_denormal_as_zero", "1") base…
-
@BradReesWork JFYI...
Currently, WM directly uses C10 API's from pytorch. Eg: `wholegraph/torch/whole_nccl_pytorch_tensor.h`. This means, similar to the pytorch backend of cugraph-ops, we'll also hav…
-
### 🚀 The feature, motivation and pitch
Triangular matrix-vector or matrix-matrix multiplication is a useful primitive in inference (because past and present tokens are taken into account, but not fu…
-
Hi,
I see there are a few SDTW implementations around. I'm mainly using Keras right now, and there are a few implementations there too. The one I have used thus far is very slow to run, as I reckon…
-
## 🚀 Feature
Implement `numpy.random.choice` equivalent.
## Motivation
In some cases, it is useful to get random samples from a torch Tensor efficiently. For instance, during the training of some…
-
C:\Users\rishu\.conda\envs\nerfstudio\lib\site-packages\torch\utils\cpp_extension.py:383: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
…
-
**Describe the bug**
We built a UNet3D image segmentation model in PyTorch (based on [this repo](https://github.com/wolny/pytorch-3dunet)) and want to start distributing it. ONNX seemed like a good o…
-
Especially batched svd.
Batched routines will increase the performance significantly on GPU.
Want this feature desperately :smile:
Cool project, wondering is there a milestone for v0.1? We'd…