[0-size Tensor No.45、48、298、99、310、124] Add 0-size Tensor support for dist/diagonal/kthvalue/logaddexp #73027
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
你的PR提交成功，感谢你对开源项目的贡献! |
co63oc
changed the title
co63oc
changed the title
co63oc
changed the title
Contributor
Author
|
CI不是修改代码错误 |
DanielSun11
reviewed
Jun 3, 2025
|
|
||
| class TestDistOp_ZeroSize(TestDistOp): | ||
| def init_case(self): | ||
| self.x_shape = (0, 1, 5, 6) |
Contributor
There was a problem hiding this comment.
单测是否可以增加一个x 或 y 只有一个为0 size Tensor的case？
| phi::Full<T, Context>( | ||
| dev_ctx, phi::IntArray(common::vectorize(output->dims())), NAN, output); | ||
| phi::Full<int64_t, Context>( | ||
| dev_ctx, phi::IntArray(common::vectorize(indices->dims())), 0, indices); |
Contributor
There was a problem hiding this comment.
output设置为nan没问题。indices设置为0，这个和torch对比过了吗？
Contributor
Author
There was a problem hiding this comment.
indices 类型是int64_t, int64_t类型没有nan
Contributor
|
其他修改没有问题了 |
|
|
Contributor
|
https://github.com/PaddlePaddle/Paddle/pull/73027/commits CLA签署有问题，里面有commit是Your Name提交的 |
Contributor
Author
|
/re-run all-failed |
Contributor
Author
|
@luotao1 CI已完成 |
wanghuancoder
approved these changes
Jun 6, 2025
Contributor
wanghuancoder
left a comment
wanghuancoder
left a comment
There was a problem hiding this comment.
这个修改了DistInferMeta，但没有修改符号推导，请 @luotao1 协调云飞帮忙确认一下。
zyfncg
approved these changes
Jun 6, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Execute Infrastructure
PR Types
Improvements
Description
paddle.dist
修改前向，反向，GPU反向和CPU反向相同
infermeta 删除numel为0判断，symbolic_shape中没有对应代码
Paddle/paddle/fluid/pir/dialect/operator/interface/infer_symbolic_shape/binary_infer_sym.cc
Line 718 in cdb4299
kernel 修改 cpu/gpu，前向和反向返回填充0
PaddleAPITest 测试已修复cuda error, 返回是torch error
paddle.diagonal
修改前向和反向，前向返回填充0
infermeta 没有修改
kernel 修改 cpu/gpu/stride
PaddleAPITest 测试已修复cuda error, 返回是torch error
paddle.kthvalue
修改前向和反向
infermeta中有axis维度不能为0的检查，和torch检查相同，没有修改
kernel 修改cpu/gpu
PaddleAPITest 已修改cuda error
torch axis维度检查
paddle.logaddexp 是python端算子，原有错误为subtract算子错误，subtract已修复，
当前PR是增加单测
PaddleAPITest 测试没有cuda error，paddle error 为测试用例形状 broadcast 错误，x, y为0的维度对应的其他值不能大于1
