NVIDIA / NVIDIA/TensorRT

Unstable inference time

Open
#4,382 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Module:Runtime triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

Hi!

I run yolo11 model inference for 1000 times in Tesla T4, but I found the time cost was very unstable.
From the cached records, I found most of the time cost was even and looked normal, but the normal ones were always interleaved with​ a few abnormal ones. For example, of the 1000 times inference records, most of the inference time cost was 2ms per image, but there were a few that cost 70ms per image.

I had tried to set a fixed card frequency but it didnt seem to work.

So can you help me with that? Thanks!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Begin by reproducing the reported YOLO11 inference timing on a Tesla T4 across 1000 runs, including the fixed-frequency setup, then identify what conditions distinguish the 2 ms runs from the occasional 70 ms runs; done means explaining or resolving the latency variation.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.