Introduce the abstraction of RunHandler which each DirectSession can use for
the duration of a single RunInternal() call from RunHandlerPool. We want to leverage this abstraction for improving the cross-session inter-op parallelism for lower latency inference in the future. In the case that global pools aren't used, this change should be a no-op. PiperOrigin-RevId: 214818187
Loading
Please sign in to comment