[Quantization speedup]support TensorRT8.0.0 #3866
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
this means we upgrade TensorRT dependency to >= 8.0? Is these upgrade available for most users? |
@J-shang Good point! Have updated quantization speedup doc. I think the departure of network definition and configuration in latest TensorRT version is rational, and support the latest version is necessary for us. I believe most of people will use the latest version especially these people who want to try mixed precision in TensorRT. |
J-shang
approved these changes
Jul 9, 2021
QuanluZhang
approved these changes
Jul 9, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR aims to support the latest TensorRT version. Current quantization speedup tool is implemented based on TensorRT7.0. However, the latest tensorrt python api has changed which separates network definition and configuration after version 8.0. All configuration of low precision have been moved to IBuilderConfig and our current implementation can't work on it (the problem raised in issue #3857 ). This PR supports the new TensorRT version and the new api.