microsoft / microsoft/onnxruntime
a perfermance issue when use onnx runtime-tensorrt
@chilo-ms is already working on this.
Since Mar 15, 2024.
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the issue
I'm using the onnx runtime-tensorrt
I found every time when I load the onnx model, it will cost some time, it may be a little short or long.
So I print the log.
I'd like to know what the red standard areas spend their time doing.
### To reproduce
just use the onnx runtime-tensorrt to run a onnx model.
### Urgency
_No response_
### Platform
Windows
### OS Version
WIN10
### ONNX Runtime Installation
Released Package
### ONNX Runtime Version or Commit ID
1.6.3
### ONNX Runtime API
C++
### Architecture
X64
### Execution Provider
TensorRT
### Execution Provider Library Version
CUDA 11.6 Tensorrt 8.6
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.