[XPU]feat: qkv_attention_fusion: qk scale can be below qk_matmul #68949
Conversation
This file contains 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! |
lj970926
reviewed
Oct 25, 2024
TR666
reviewed
Oct 25, 2024
houj04
reviewed
Oct 28, 2024
houj04
approved these changes
Oct 28, 2024
fxfxfxfxfxfxfxfx
pushed a commit
to fxfxfxfxfxfxfxfx/Paddle
that referenced
this pull request
Oct 29, 2024
…ddlePaddle#68949) * [XPU]feat: qkv_attention_fusion: qk scale can be below qk_matmul * add xpu ir qkv attention fuse test case * remove test skip * add kl3 unit test, fix unit test * update comment
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Outdated suggestions cannot be applied.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
Inference
PR Types
New features
Description
modify ir: qk scale can be below qk_matmul
add arg
scale_above_qkto determinescale's position