pytorch/serve

Confused about Cumulative Inference Duration vs. PredictionTime

Open

#1,698 opened on Jun 20, 2022

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Java (790 forks)batch import
help wantedquestion

Repository metrics

Stars
 (3,844 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

📚 The doc issue

I am running a model on TorchServe and I am trying to see how long it takes for inference. If I use logging and view the logs, then I can see there is something called PredictionTime: image

However, if I use the Metrics API, then I got something called "Cumulative Inference Duration" image

And in terms of values those 2 are very different. So I am not sure which one should I use to measure the total inference time for my requests?

Btw, there is also something else called HandlerTime in the logs image

What does it mean? Where can I find related information about what are the meanings of these metrics?

Thanks,

Suggest a potential alternative/fix

No response

Contributor guide

Research direction
Review TorchServe documentation and source code to understand the definitions of Cumulative Inference Duration, PredictionTime, and HandlerTime metrics. Check the metrics API and logging output to clarify which metric corresponds to total inference time.
Tech stack
javapython
Domain
backendobservabilityapi
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
1
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
TorchServe basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80