* support pure bfloat16

* support bf16 linear

* update PR to pass CI

* tiny fix where_grad_kernel.cu

* add bfloat16 to selu_grad to pass CI

* fix selu grad compilation error

* add gelu

* fix gelu

* add log_softmax

* add prelu kernel and prelu/gelu/logsoftmax infershape

* fix

* fix

* fix

* fix

* fix ci

* log_softmax rewrite

* fix

* fix

* fix conflict

* fix compile error

* fix comment

* fix

* ci_fix
Co-authored-by: NYan Li <liyan665@gmail.com>