-
Notifications
You must be signed in to change notification settings - Fork 1.6k
[XPU] add interpolate fp16, fix reshape bug, add l3_autotune api. tes… #9259
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
|
Thanks for your contribution! |
|
LGTM |
liyancas
left a comment
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
|
LGTM |
| // **DEPRECATED**, use set_xpu_l3_cache_method() in the future | ||
| void set_xpu_workspace_l3_size_per_thread(int l3_size = 0x4000000); | ||
| void set_xpu_l3_cache_method(size_t l3_size, bool locked = false); | ||
| void set_xpu_l3_cache_autotune(bool autotune = true); |
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.
是公开api吗,公开api 需要补到C++ 文档中
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.
并补充相关单测到paddle_api_test.cc中
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.
相关的python API 需要考虑是否补充
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.
收到,该接口的使用说明在下个pr中补充
|
LGTM |
| std::vector<LoD> last_input_lods_{}; | ||
| std::vector<DDimLite> last_output_shapes_{}; | ||
| std::vector<LoD> last_output_lods_{}; | ||
| // last shape tensor vector cache. |
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.
std::vector<DDimLite> last_input_shapes_{};
std::vector<LoD> last_input_lods_{};
std::vector<DDimLite> last_output_shapes_{};
std::vector<LoD> last_output_lods_{};子类里为什么要重新声明这四个成员变量,为什么不直接使用 OperatorBase 基类里声明的同名变量
hong19860320
left a comment
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
…t=develop