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
Since TRT 8.6 EA, the optimization level of building engine can be determined by users with new API setBuilderOptimizationLevel.
Hence, this PR provides an interface in Paddle Inference for users to set the optimization level.
void SetTensorRtOptimizationLevel(int) : to set the optimization level
int tensorrt_optimization_level() : return the optimization level (default is 3 if not set)
This API accepts level in the range [0, 5], and higher optimization level allows the optimizer to spend more time searching for optimization opportunities. The default optimization level is 3.
你的PR提交成功,感谢你对开源项目的贡献!
请关注后续CI自动化测试结果,详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.
2023-09-11 14:47:10 0. You must have one QA (XieYunshen(Recommend) or chalsliu) approval for setting parameter RUN_TYPE as EXCLUSIVE, DIST, NIGHTLY, EXCLUSIVE:NIGHTLY or DISTNIGHTLY, or setting parameter SERIAL, or setting TIMEOUT properties.
2023-09-11 14:47:10 The corresponding lines are as follows:
2023-09-11 14:47:10 test/ir/inference/CMakeLists.txt
2023-09-11 14:47:10 + set_tests_properties(test_trt_optimization_level PROPERTIES TIMEOUT 300)
2023-09-11 14:47:10 For more information, please refer to:https://github.com/PaddlePaddle/Paddle/wiki/PaddlePaddle-Unit-test-specification
2023-09-11 14:47:10 There are 1 approved errors.
PR-CI-Static-Check
2023-09-11 17:51:55 Please find RD for approval first, and then find TPM for approval.
2023-09-11 17:51:55 0. You must have one RD (XiaoguangHu01, jeff41404, lanxianghit or qingqing01) approval for API change.
2023-09-11 17:51:55 and one TPM approval for API change:
2023-09-11 17:51:55 jzhang533/ZhangJun, sunzhongkai588/SunZhongKai, dingjiaweiww/DingJiaWei, Ligoml/LiMengLiu for general APIs.
2023-09-11 17:51:55 liuTINA0907/LiuShuangQiao for distributed related APIs.
2023-09-11 17:51:55 leiqing1/LeiQing for inference related APIs.
2023-09-11 17:51:55 1. You must have one RD (XiaoguangHu01, jeff41404, lanxianghit or qingqing01) approval for API change.
2023-09-11 17:51:55 and one TPM approval for API change:
2023-09-11 17:51:55 jzhang533/ZhangJun, sunzhongkai588/SunZhongKai, dingjiaweiww/DingJiaWei, Ligoml/LiMengLiu for general APIs.
2023-09-11 17:51:55 liuTINA0907/LiuShuangQiao for distributed related APIs.
2023-09-11 17:51:55 leiqing1/LeiQing for inference related APIs.
2023-09-11 17:51:55 2. You must have one TPM approval for API documents change:
2023-09-11 17:51:55 jzhang533/ZhangJun, sunzhongkai588/SunZhongKai, dingjiaweiww/DingJiaWei, Ligoml/LiMengLiu for general API docs.
2023-09-11 17:51:55 liuTINA0907/LiuShuangQiao for distributed related API docs.
2023-09-11 17:51:55 leiqing1/LeiQing for inference related API docs.
2023-09-11 17:51:55
2023-09-11 17:51:55 There are 3 approved errors.
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
New features
PR changes
APIs
Description
Since TRT 8.6 EA, the optimization level of building engine can be determined by users with new API
setBuilderOptimizationLevel
.Hence, this PR provides an interface in Paddle Inference for users to set the optimization level.
void SetTensorRtOptimizationLevel(int)
: to set the optimization levelint tensorrt_optimization_level()
: return the optimization level (default is 3 if not set)This API accepts level in the range [0, 5], and higher optimization level allows the optimizer to spend more time searching for optimization opportunities. The default optimization level is 3.