Yong
Yong
@zhangqiaorjc @martinwicke hello could you please help take a look? thanks.
@mhong Thanks for the reply. We are currently investigating how to leverage MLIR Compiler capability with the new TFRT in order to improve the machine learning workload performance inside Alibaba....
> TFRT will support different flavors of kernels: codegen'ed (via xla, mlir, or other technology), hand-written (e.g. via Eigen), and library-based (e.g. by calling into cuDNN). > > codengen'ed kernels...
> When calling existing kernels, indeed some overhead will be incurred, but not all kernel invocation will be on the critical path of the model computation. Our goal in that...