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.

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

update paddle predictor #2855

Open
wants to merge 4 commits into
base: develop
Choose a base branch
from

Conversation

TingquanGao
Copy link
Collaborator

  1. support pir trt;
  2. optimize trt;

Copy link

paddle-bot bot commented Jan 15, 2025

Thanks for your contribution!

@TingquanGao TingquanGao mentioned this pull request Jan 15, 2025
@@ -47,6 +47,36 @@ def collect_trt_shapes(
predictor.run()


def convert_trt(mode, pp_model_path, trt_save_path, trt_dynamic_shapes):
from lazy_paddle.tensorrt.export import (

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lazy_paddle是什么?

# Create TensorRTConfig
trt_config = TensorRTConfig(inputs=trt_inputs)
trt_config.precision_mode = precision_map[mode]
trt_config.save_model_dir = trt_save_path
Copy link

@lizexu123 lizexu123 Jan 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

建议再增加一个传入,禁止哪些op进入trt,比如trt_config.disable_ops="pd_op.xxx",现在这套好像不能实现这个功能,还有就是是跑fp16的时候,强制将哪些op转换成fp32推理

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants