Gsplat

What's Changed
* Eval table by AdamRashid96 in https://github.com/nerfstudio-project/gsplat/pull/134
* add device guard by liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/135
* Fix backprop grad of cov2d / scales and unit tests by jb-ye in https://github.com/nerfstudio-project/gsplat/pull/136

New Contributors
* AdamRashid96 made their first contribution in https://github.com/nerfstudio-project/gsplat/pull/134

**Full Changelog**: https://github.com/nerfstudio-project/gsplat/compare/v0.1.6...v0.1.7

What's new
The python interface for `tile_bounds` has been abstracted away, and instead project and rasterize take in a `block_width` parameter controlling the tile size as well as the CUDA block size. CUDA was refactored to allow dynamic block sizes, which enables ND rasterization speedups by taking better advantage of shared memory.

What's new?
- Improved pytorch implementation of `project_gaussians` inside _torch_impl.py
- Screen space blur compensation for rasterizing tiny gaussians from Mip-Splatting
- Bugfixes

What's Changed
Fix a major bug in rasterization since version `0.1.0`. ([Issue](https://github.com/nerfstudio-project/gsplat/issues/111) and [PR](https://github.com/nerfstudio-project/gsplat/pull/112))

What's changed
* Alpha rendering and supervision with `return_alpha` flag in `rasterize.py`
* Fix bug with 0 gaussians in view

What's Changed
* Fixing latent issue with single intersection
* API update: Function.apply() will be deprecated soon. It's recommend to directly call the python functions. The full list of updates:
* `ProjectGaussians.apply` -> `project_gaussians`
* `RasterizeGaussians.apply` / `NDRasterizeGaussians.apply` -> `rasterize_gaussians`
* `BinAndSortGaussians.apply` -> `bin_and_sort_gaussians`
* `ComputeCumulativeIntersects.apply` -> `compute_cumulative_intersects`
* `ComputeCov2dBounds.apply` -> `compute_cov2d_bounds`
* `GetTileBinEdges.apply` -> `get_tile_bin_edges`
* `MapGaussiansToIntersects.apply` -> `map_gaussian_to_intersects`
* `SphericalHarmonics.apply` -> `spherical_harmonics`