-
Notifications
You must be signed in to change notification settings - Fork 5.9k
[Inference] Split core converter file into several files #67877
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
Conversation
|
你的PR提交成功,感谢你对开源项目的贡献! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个是不是应该叫unary.py?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这些文件命名与python对应的api接口是统一的
| return relu_layer.get_output(0) | ||
|
|
||
|
|
||
| @converter_registry.register("pd_op.softmax", trt_version="8.x") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个属于activation吗?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
同上,softmax api在paddle里是放在activation里边的
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR Category
Inference
PR Types
Others
Description
card-71500
本PR做了如下工作:
1,将算子Converter拆解归类到多个代码文件中,方便管理及加速Converter并行开发
2,修复generic_plugin下未正常切换流的问题
3,优化Converter接口设计,改为返回TRT Layer的输出,解决潜在多输出Layer无法与Paddle算子对齐的问题