[Paddle-TRT] upgrade EnqueueV2 to EnqueueV3 #60807
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
|
手机坏了，暂时登陆不了Lizexu123的号。 |
vivienfanghuagood
approved these changes
Jan 19, 2024
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Outdated suggestions cannot be applied.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.
PR types
Others
PR changes
Others
Description
Pcard-71501
TensorRT执行器升级，enqueueV2升级enqueueV3
使用条件:TensorRT>8.5
在A10上测量了54个模型，与enqueueV2推理时间持平。Paddle-trt的执行器功能升级。
注意:以后TensorRT 8.5版本以后，Paddle-trt都使用enqueueV3接口推理，请注意不要使用setBindingDimension和setInputShapeBinding，请使用setInputShape和setTensorAddress替代。
测试模型，单测不要删除任何op，否则会导致core down。
enqueue: oldest api, support implicit batch, is deprecated.
enqueueV2: replacement of enqueue, support explict batch. is deprecated now.
enqueueV3: latest api, support data dependent shape, recommend to use now.
Please check TensorRT: nvinfer1::IExecutionContext Class Reference 153 for details.
TensorRT runtime time (inference)
execution tensor: Runtime: IExecutionContext->setInputShape + setTensorAddress
shape tensor: IExecutionContext->setTensorAdress
注意:两者使用的API是不同的，shape tensor的时候，只使用setTensorAddress，shape_tensor I/O的address需要的是cpu point