Exllamav2

- Adds support for Cohere models
- N-gram decoding
- A few bugfixes
- Lots of optimizations

**Full Changelog**: https://github.com/turboderp/exllamav2/compare/v0.0.15...v0.0.16

- Adds Q4 cache mode
- Support for StarCoder2
- Minor optimizations and a couple of bugfixes

**Full Changelog**: https://github.com/turboderp/exllamav2/compare/v0.0.14...v0.0.15

Adds support for Qwen1.5 and Gemma architectures.

Various fixes and optimizations.

**Full Changelog since 0.0.13**: https://github.com/turboderp/exllamav2/compare/v0.0.13...v0.0.14

**Full Changelog**: https://github.com/turboderp/exllamav2/compare/0.0.13.post1...0.0.13.post2

Fixes inference on models with vocab sizes that are not multiples of 32

This release is mostly to update the prebuilt wheels to Torch 2.2, since it won't load extensions built for earlier versions.

Adds dynamic temperature and quadratic sampling. Fixes performance degradation on some GPUs after batch optimizations and various other little things.