Ruilong Li(李瑞龙)

Yeah floating error is always a headache -- currently i dont have a better way to deal with it

Hi I'm not supporting that in this repo because I was hacking some CUDA code to make that happen, but I don't want to mess up the API in this...

Hi for your questions: 1/ It return *all* samples for a batch of rays, in a concatenated tensor. See [here](https://github.com/KAIR-BAIR/nerfacc/blob/561c6c5ae2a44f902f9f8bba3e53e7df78fdbe92/nerfacc/data_specs.py#L13-L27) for more details. 2/ Yeah the `t` being used to...

Thanks for pointing this out. Yeah having that marked on the doc would be nice. I will try to find some time to do it.