Merge branch 'ck_tile/fa_bwd_opt' of https://github.com/ROCm/composable_kernel...

Merge branch 'ck_tile/fa_bwd_opt' of https://github.com/ROCm/composable_kernel into ck_tile/fa_bwd_opt

example/ck_tile/01_fmha/codegen/ops/fmha_bwd.py

@@ -490,6 +490,7 @@ def get_bwd_dq_dk_dv_blobs(kernel_filter : Optional[str], receipt, mask_impl) ->
             if receipt == 2:
                     cond = dtype in ['fp16', 'bf16']
                     cond &= bias in ['no', 'alibi']
+                    cond &= dropout in ['no', 'dropout_wg32',  'dropout_wg16']
                     if not cond:
                         continue
             api_pool.register_dq_dk_dv_traits(k.api_trait())