Skip to content

[Custom Device]如何使用融合算子conv_fusion_op #60476

@engineer1109

Description

@engineer1109

请提出你的问题 Please ask your question

我在CUDA和Custom Device都同时启用的时候,可以使用OP conv_fusion_op 以及自定义kernel conv2d_fusion(OpenCL)
在Paddle Inference添加Pass的时候 conv_elementwise_add_act_fuse_pass 也是有效的。

但是如果把编译CUDA关闭了,只开启Custom Device。就会出现OP找不到的问题。

terminate called after throwing an instance of 'phi::enforce::EnforceNotMet'
  what():  (NotFound) Operator (conv2d_fusion) is not registered.
  [Hint: op_info_ptr should not be null.] (at /media/wjl/D2/github/fork/10/Paddle/paddle/fluid/framework/op_info.h:149)

那么我该如何让Custom Device找到OP conv_fusion_op?

Metadata

Metadata

Assignees

Labels

PFCCPaddle Framework Contributor Club,https://github.com/PaddlePaddle/community/tree/master/pfccstatus/close已关闭type/question用户提问

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions