BentoML
                                
                                 BentoML copied to clipboard
                                
                                    BentoML copied to clipboard
                            
                            
                            
                        Add more debug/info logs runner indicating adaptive batching logic
Is your feature request related to a problem? Please describe.
Currently there is not too much visibility for the user to visualize or to understand how BentoML's micro-batching works. having more logs around how BentoML makes a decision and what is happening in the batching layer should help with that.
cc @bojiang
Describe the solution you'd like
Describe alternatives you've considered
Additional context
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
In debug mode, RunnerApp should:
- log the batch size for each run
- log the latency for each run