Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Paddle-TRT] allow plugin fall back to fp16 when int8 #50554

Merged
merged 4 commits into from
Feb 24, 2023
Merged

[Paddle-TRT] allow plugin fall back to fp16 when int8 #50554

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4020a92
allow fall back to fp16 when int8
zhoutianzi666 Feb 16, 2023
6ead908
refine code
zhoutianzi666 Feb 16, 2023
ea7fda0
refine code
zhoutianzi666 Feb 16, 2023
1032bda
refine code
zhoutianzi666 Feb 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion paddle/fluid/inference/tensorrt/engine.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,9 @@ class TensorRTEngine {
bool WithFp16() {
bool enable_fp16 = (precision_ == AnalysisConfig::Precision::kHalf);
bool support_fp16 = infer_builder_->platformHasFastFp16();
return enable_fp16 && support_fp16;
// below is consistent with setFlag in engine.cc
bool fall_back_fp16 = WithInt8() && !use_dla_;
return (enable_fp16 || fall_back_fp16) && support_fp16;
}

bool WithInt8() {
Expand Down