George

icon indicating a website link https://scholar.google.com/citations?user=y_jNFVgAAAAJ icon indicating an email [email protected]

icon company Tsinghua University icon location Beijing icon location I'm an undergraduate student in Department of Computer Science and Technology, Tsinghua University

Results 5 issues of George

Update quantization.py

1 comment

torch.Tensor.is_cuda is an attribute, not a function this pr will solve the TypeError when calling `sparse_quantize` when using torch.Tensor as input ![image](https://user-images.githubusercontent.com/51397242/169657470-58426f1a-4258-4c69-b86c-6cd98524bb5c.png)

Fail to run with CUDA 11.3

1 comment

Hi! This is a really exciting work, and thanks for your effort in this implementation. Unfortunately, I cannot recreate the results on my own server equipped with a NVIDIA A100...

Update README.MD

propose a change in requirements to build up the Conda env

[DITO] Fail to launch demo: The current platform CUDA is not among the platforms required by the module: [CPU]

4 comment

I tried to launch the demo app of your amazing work DITO by `python dito/demo.py` in the subdirectory of `fvlm/` (following instructions at [fvlm/dito/README.md](https://github.com/google-research/google-research/raw/master/fvlm/dito/README.md)), but these errors occur: ``` 2023-11-16...

fix compile error for knn with pytorch 1.11+