Ck tile/kvcache

[rocking5566]

Integrate CK's append kv and split kv kernel from this PR
ROCm/composable_kernel#1387

[Cydia2018]

Thanks for your work, I would like to know when paged kv in "flash_attn_varlen_func" will be supported.

see https://github.com/ROCm/flash-attention/blob/ck_improve_v0.1.1/csrc/flash_attn_ck/mha_varlen_fwd.cpp#L186

[rocking5566]

Thanks for your work, I would like to know when paged kv in "flash_attn_varlen_func" will be supported.

see https://github.com/ROCm/flash-attention/blob/ck_improve_v0.1.1/csrc/flash_attn_ck/mha_varlen_fwd.cpp#L186

This will be supported recently.