[runtime] reduce set_input and set_input_zero_copy overhead #3805
  Add this suggestion to a batch that can be applied as a single commit.
  This suggestion is invalid because no changes were made to the code.
  Suggestions cannot be applied while the pull request is closed.
  Suggestions cannot be applied while viewing a subset of changes.
  Only one suggestion per line can be applied in a batch.
  Add this suggestion to a batch that can be applied as a single commit.
  Applying suggestions on deleted lines is not supported.
  You must change the existing code in this line in order to create a valid suggestion.
  Outdated suggestions cannot be applied.
  This suggestion has been applied or marked resolved.
  Suggestions cannot be applied from pending reviews.
  Suggestions cannot be applied on multi-line comments.
  Suggestions cannot be applied while the pull request is queued to merge.
  Suggestion cannot be applied right now. Please check back later.
  
    
  
    
Two optimizations:
std::unordered_mapto reduce lookup time, which could be significant where the number of inputs is largevectorto track the corresponding input arg dltensor* so we don't need to iterate through the inputs of all notes to look them up every single time. This is a followup to [Runtime] Enable set_input_zero_copy in GraphRuntime #3416@yinghai, @tqchen please review