Add padding-free to bamba (#35861)
* add seq_idx and fa kwargs
* update tests
* docs and grad ckpt support
* fmt
* better names
* test_raise_missing_padding_free_kwarg_errs
* + seq_idx in doc strings
* padding free training docs
* add link to pr plots
* raise err on attn_mask with padding free
* rm raising missing padding free err test
* BambaFlashAttentionKwargs
* run modular util for modular_granitemoehybrid.py