add inference api:exp_specify_tensorrt_subgraph_precision #62402
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! |
lizexu123
changed the title
yuanlehome
reviewed
Mar 6, 2024
| bool enable_fp16 = false; | ||
| if (precision_mode == phi::DataType::FLOAT16) enable_fp16 = true; | ||
| auto enable_int8 = Get<bool>("enable_int8"); | ||
|
|
||
| for (auto para : parameters) { |
There was a problem hiding this comment.
Suggested change
| for (auto para : parameters) { | |
| for (const auto& para : parameters) { |
| } | ||
| } | ||
|
|
||
| for (auto para : parameters) { |
There was a problem hiding this comment.
Suggested change
| for (auto para : parameters) { | |
| for (const auto& para : parameters) { |
| auto trt_params_run_bfp16 = | ||
| Get<std::vector<std::string>>("trt_parameter_run_bfp16"); | ||
|
|
||
| for (auto para : parameters) { |
There was a problem hiding this comment.
Suggested change
| for (auto para : parameters) { | |
| for (const auto& para : parameters) { |
Comment on lines
465
to
471
| <<<<<<< HEAD | ||
| CP_MEMBER(trt_parameters_run_fp16_); | ||
| CP_MEMBER(trt_parameters_run_int8_); | ||
| CP_MEMBER(trt_parameters_run_bfp16_); | ||
| ======= | ||
| CP_MEMBER(trt_forbid_dynamic_op_) | ||
| >>>>>>> 2ca34a759a255660844914004f2b8b59057ce0fe |
| @@ -813,6 +813,10 @@ struct PD_INFER_DECL AnalysisConfig { | |||
| void Exp_DisableTensorRtSubgraph( | |||
| const std::vector<std::string>& var_name_not_trt); | |||
|
|
|||
| void Exp_Specify_TensorRT_Subgraph_Precision( | |||
yuanlehome
reviewed
Mar 7, 2024
| @@ -813,6 +813,10 @@ struct PD_INFER_DECL AnalysisConfig { | |||
| void Exp_DisableTensorRtSubgraph( | |||
| const std::vector<std::string>& var_name_not_trt); | |||
|
|
|||
| void Exp_SpecifyTensorRTSubgraphPrecision( | |||
yuanlehome
previously approved these changes
Mar 7, 2024
zhoutianzi666
approved these changes
Mar 11, 2024
hitywt
pushed a commit
to hitywt/Paddle
that referenced
this pull request
Mar 11, 2024
…le#62402) add inference api:exp_specify_tensorrt_subgraph_precision (PaddlePaddle#62402)
hitywt
pushed a commit
to hitywt/Paddle
that referenced
this pull request
Mar 11, 2024
…le#62402) add inference api:exp_specify_tensorrt_subgraph_precision (PaddlePaddle#62402)
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
New features
PR changes
Others
Description
Pcard-71501
推理新增指定trt子图，让指定的trt子图跑float16，让指定的的trt子图跑int8，让指定的trt子图跑bf16(trt9.0版本以上才支持)
使用说明:
第一个参数，指定跑fp16的权重的名称，第二个参数，指定跑int8的权重的名称。第三个参数，指定跑bfp16的权重的名称。
只需要指定tensorrt_engine中一个权重的名称即可。
注释掉config.disable_glog_info()可以看日志，跑了fp16和bfp16。
也可以通过Nsight System 查看kernel的精度