Add QuaRot (RTN) [WIP]

[nailimixaM]

Questions:

• Adding quarot as a new package under src/: should we modify the toml so that if someone wants only one of SliceGPT or QuaRot we don't install extra dependencies only used by the other? e.g. fast_hadamard_transform is only used by QuaRot [done]
• Should we be moving non-SliceGPT-specific things like model downloading from HF, distributing models over GPUs, dataloading, etc to a common dir? [later PR]
• Bump up the version number in toml file [done]

Reviewers, please ignore the following files as they are exact duplicated from the slicegpt side of the codebase:

• hf_utils.py
• layernorm_fusion.py

[pashminacameron]

Questions:

• Adding quarot as a new package under src/: should we modify the toml so that if someone wants only one of SliceGPT or QuaRot we don't install extra dependencies only used by the other? e.g. fast_hadamard_transform is only used by QuaRot
• Should we be moving non-SliceGPT-specific things like model downloading from HF, distributing models over GPUs, dataloading, etc to a common dir?
• Bump up the version number in toml file?

Yes to all. It will be a major version bump, so we can make breaking changes. It might also be a good opportunity to move to package versions for transformers and lm-eval rather than using specific git commits.