Support trt engine auto build in runtime for dynamic shape #52162
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! |
JZZ-NOTE
force-pushed
the
trt_auto_dynamic_shape
branch
from
bc88932
to
bd58a23
Compare
yuanlehome
reviewed
Apr 11, 2023
| @@ -199,7 +199,7 @@ void IRPassManager::CreatePasses(Argument *argument, | |||
| optim_cache_dir)); | |||
| } | |||
| pass->Set("model_opt_cache_dir", new std::string(optim_cache_dir)); | |||
| } else if (use_static_engine || enable_int8) { | |||
| } else { | |||
| &min_shape_tensor, | ||
| &max_shape_tensor, | ||
| &opt_shape_tensor); | ||
| if (shape_range_info_path != "") { |
| &max_shape_tensor, | ||
| &opt_shape_tensor); | ||
| } else { | ||
| int fd = |
There was a problem hiding this comment.
文件打开读写这一块c++有封装好的api吧，用c?
| void EnableTunedTensorRtDynamicShape(const std::string& shape_range_info_path, | ||
| bool allow_build_at_runtime = true); | ||
| void EnableTunedTensorRtDynamicShape( | ||
| const std::string shape_range_info_path = "", |
| @@ -441,6 +441,9 @@ class TensorRTEngine { | |||
| void SetUseDLA(bool use_dla) { use_dla_ = use_dla; } | |||
| void SetDLACore(int dla_core) { dla_core_ = dla_core; } | |||
| void SetWithErnie(bool with_ernie) { with_ernie_ = with_ernie; } | |||
| void SetWithDynamicShape(bool with_dynamic_shape) { | |||
There was a problem hiding this comment.
新增了这个接口，第250行附近的逻辑可以给删了
jiweibo
reviewed
Apr 11, 2023
jiweibo
reviewed
Apr 11, 2023
| @@ -1434,7 +1434,7 @@ bool AnalysisConfig::shape_range_info_collected() const { | |||
| } | |||
|
|
|||
| void AnalysisConfig::EnableTunedTensorRtDynamicShape( | |||
| const std::string &shape_range_info_path, bool allow_build_at_runtime) { | |||
| @@ -14,6 +14,7 @@ | |||
| // limitations under the License. | |||
|
|
|||
| #include "paddle/fluid/inference/analysis/ir_passes/tensorrt_subgraph_pass.h" | |||
| #include <fcntl.h> | |||
| @@ -224,6 +224,7 @@ class TensorRTEngine { | |||
| AnalysisConfig::Precision precision = AnalysisConfig::Precision::kFloat32, | |||
| TRTInt8Calibrator* calibrator = nullptr, | |||
| int device_id = 0, | |||
| bool with_dynamic_shape = false, | |||
There was a problem hiding this comment.
为什么要加上这一个选项呢？
以前是根据啥来区分是动态shape还是静态shape呢？
|
leiqing1
approved these changes
Apr 14, 2023
jjyaoao
pushed a commit
to jjyaoao/Paddle
that referenced
this pull request
Apr 19, 2023
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
Describe
添加配置Paddle-Trt动态Shape的新方式：
两个可改进的点：