What's Changed
* Breaking: Rename GRLIR to GRL by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/120
* Breaking: More guarantees for `minimum` and `multiple_of` in `SizeRequirements` by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/124
* Breaking: Bring `model.to` signature in line with PyTorch `module.to` by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/133
* Breaking: Verify dtype in `to` by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/135
* Save Real-CUGAN models correctly by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/119
* Fix ESRGAN size requirement by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/121
* Clamp output tensor to guarantee output range by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/127
* Deduplicate tensor pad-to-size code by akx in https://github.com/chaiNNer-org/spandrel/pull/104
* Add `dtype`, `cpu`, and `cuda` to model API by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/132
New architectures
* Add support for SAFMN by RunDevelopment in https://github.com/chaiNNer-org/spandrel/pull/130
**Full Changelog**: https://github.com/chaiNNer-org/spandrel/compare/v0.1.8...v0.2.0