RuntimeError: value cannot be converted to type int without overflow

[xiaoroubao1996]

Hi, I got the following error when using 3090.
I totally adopted your virtual environment. Is there any solution?

  File "run.py", line 172, in <module>
    train(args, cfg, data_dict, jax_key, writer)
  File "/home/nikki/Donghao/Mud/PureClipNeRF/train_imp.py", line 590, in train
    scene_rep_reconstruction(
  File "/home/nikki/Donghao/Mud/PureClipNeRF/train_imp.py", line 371, in scene_rep_reconstruction
    render_result = model(rays_o, rays_d, viewdirs, global_step=global_step, **render_kwargs)
  File "/home/nikki/anaconda3/envs/python38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/nikki/Donghao/Mud/PureClipNeRF/lib/dvgo_imp.py", line 395, in forward
    ray_pts, ray_id, step_id = self.sample_ray(
  File "/home/nikki/Donghao/Mud/PureClipNeRF/lib/dvgo_imp.py", line 343, in sample_ray
    ray_pts, mask_outbbox, ray_id, step_id, N_steps, t_min, t_max = render_utils_cuda.sample_pts_on_rays(
RuntimeError: value cannot be converted to type int without overflow