[Operator]Delete XShape for squeeze output #67355
Merged
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! |
winter-wang
previously approved these changes
Aug 13, 2024
zhangbo9674
previously approved these changes
Aug 13, 2024
zyfncg
previously approved these changes
Aug 13, 2024
Aurelius84
dismissed stale reviews from zyfncg, zhangbo9674, and winter-wang
via
0f25bf0
winter-wang
approved these changes
Aug 14, 2024
Hongqing-work
approved these changes
Aug 14, 2024
gongshaotian
approved these changes
Aug 14, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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
Operator Mechanism
PR Types
Deprecations
Description
Pcard-67164
What's New?
退场了动态图和新IR下 squeeze 算子中的XShape字段，实现动静统一，具体改动：
1. 在legacy里隔离旧静态图的定义
动态图和新IR的算子体系使用了 phi/ops.yaml，实现理想态的动静统一。为了保证旧IR下的算子表示层面的兼容，因此在legacy目录下static_ops.yaml和static_backward.yaml单独定义了squeeeze的前反向算子，Kernel使用 squeeze_with_xshape，并在Kernel定义中标记FIXME
2. 需要对squeeze2_grad的转换规则做添加
test_seq2seq 和 test_bmn 两个单测依赖squeeze2_grad的转换规则，并在单测体系下单独添加了test_squeeze_grad_translator.py 单测
3. 修改了pd_to_cinn pass 逻辑
移除了 pd_to_cinn_pass 中 SqueezeOpPattern 中的 ReplaceWithCinnReshape 逻辑，无需再处理XShape
4. 部分融合Pass需要移除XShape的DRR定义
目前框架里主要涉及squeeze_transpose_onednn_fuse_pass和fused_rotary_position_embedding_pass两个Pass