Issu in time inference
Open
@zerollzeng is already working on this.
Since Jan 6, 2023.
triaged
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
Hi All,
With tensorRT 8.5, cuddn 8.6.0 I make an inference with cuda 11.8
I obtain globally in term of time processing -> 280 ms on an T4.
Previously i was on cuda 10 tensorRT 8.3 and cuddn 8.3.3 -> I had a time processing of 150ms.
My driver is 522.30.
Could you please give a piece of advice ?
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.