The context-caching options added in #62 (cache_context, maybe_quantize_kv_cache, and keep_cache_on_device) are available on TabFMClassifier and TabFMRegressor, but are not currently mentioned in the README.
It would be useful to document how to enable them and their defaults. A short addition alongside the existing usage examples could make these options easier to discover.
I’m happy to submit a PR for this.
The context-caching options added in #62 (cache_context, maybe_quantize_kv_cache, and keep_cache_on_device) are available on TabFMClassifier and TabFMRegressor, but are not currently mentioned in the README.
It would be useful to document how to enable them and their defaults. A short addition alongside the existing usage examples could make these options easier to discover.
I’m happy to submit a PR for this.