You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains hidden or 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
qingqing01
changed the title
[Paddle TensorRT] pir support TensorRT 8.x
[Paddle TensorRT] Refactor subgrah segmentation and operator convter of Paddle TensorRT base on PIR.
Aug 8, 2024
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 Category
Inference
PR Types
New features
Description
card-71500
Paddle TensorRT整体分为5大模块:

本PR完成了以下3大模块:
2.Marker Pass:用来标记Op是否可以进入TensorRT子图
3.Partition Pass:子图切割,用来将标记好的Op划分成一个子图,该子图作为一个TensorRT Group
4.TensorRT Converter:将分割好的TensorRT Group中的Paddle算子进行映射,变为一个TensorRT子图并在PIR Program中创建TensorRT EngineOP
其余模块见pr#64995
1.Warmup and Collect Shape:用来收集以及分析PIR Program中各个算子的输入Shape的最大值、最小值及最优值,为后续TensorRT Engine的构建提供shape信息
5.TensorRT Engine Instruction:执行构建好的TensorRTEngineOp,并将TensorRT引擎中的输入输出数据与Paddle执行框架中的数据进行交换与更新