| CARVIEW |
Select Language
HTTP/2 200
date: Thu, 24 Jul 2025 23:45:56 GMT
content-type: text/html; charset=utf-8
cache-control: no-cache
content-security-policy: default-src 'none'; base-uri 'self'; child-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/; connect-src 'self' uploads.github.com www.githubstatus.com collector.github.com raw.githubusercontent.com api.github.com github-cloud.s3.amazonaws.com github-production-repository-file-5c1aeb.s3.amazonaws.com github-production-upload-manifest-file-7fdce7.s3.amazonaws.com github-production-user-asset-6210df.s3.amazonaws.com *.rel.tunnels.api.visualstudio.com wss://*.rel.tunnels.api.visualstudio.com objects-origin.githubusercontent.com copilot-proxy.githubusercontent.com proxy.individual.githubcopilot.com proxy.business.githubcopilot.com proxy.enterprise.githubcopilot.com *.actions.githubusercontent.com wss://*.actions.githubusercontent.com productionresultssa0.blob.core.windows.net/ productionresultssa1.blob.core.windows.net/ productionresultssa2.blob.core.windows.net/ productionresultssa3.blob.core.windows.net/ productionresultssa4.blob.core.windows.net/ productionresultssa5.blob.core.windows.net/ productionresultssa6.blob.core.windows.net/ productionresultssa7.blob.core.windows.net/ productionresultssa8.blob.core.windows.net/ productionresultssa9.blob.core.windows.net/ productionresultssa10.blob.core.windows.net/ productionresultssa11.blob.core.windows.net/ productionresultssa12.blob.core.windows.net/ productionresultssa13.blob.core.windows.net/ productionresultssa14.blob.core.windows.net/ productionresultssa15.blob.core.windows.net/ productionresultssa16.blob.core.windows.net/ productionresultssa17.blob.core.windows.net/ productionresultssa18.blob.core.windows.net/ productionresultssa19.blob.core.windows.net/ github-production-repository-image-32fea6.s3.amazonaws.com github-production-release-asset-2e65be.s3.amazonaws.com insights.github.com wss://alive.github.com api.githubcopilot.com api.individual.githubcopilot.com api.business.githubcopilot.com api.enterprise.githubcopilot.com; font-src github.githubassets.com; form-action 'self' github.com gist.github.com copilot-workspace.githubnext.com objects-origin.githubusercontent.com; frame-ancestors 'none'; frame-src viewscreen.githubusercontent.com notebooks.githubusercontent.com; img-src 'self' data: blob: github.githubassets.com media.githubusercontent.com camo.githubusercontent.com identicons.github.com avatars.githubusercontent.com private-avatars.githubusercontent.com github-cloud.s3.amazonaws.com objects.githubusercontent.com release-assets.githubusercontent.com secured-user-images.githubusercontent.com/ user-images.githubusercontent.com/ private-user-images.githubusercontent.com opengraph.githubassets.com copilotprodattachments.blob.core.windows.net/github-production-copilot-attachments/ github-production-user-asset-6210df.s3.amazonaws.com customer-stories-feed.github.com spotlights-feed.github.com objects-origin.githubusercontent.com *.githubusercontent.com; manifest-src 'self'; media-src github.com user-images.githubusercontent.com/ secured-user-images.githubusercontent.com/ private-user-images.githubusercontent.com github-production-user-asset-6210df.s3.amazonaws.com gist.github.com; script-src github.githubassets.com; style-src 'unsafe-inline' github.githubassets.com; upgrade-insecure-requests; worker-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/
referrer-policy: no-referrer-when-downgrade
server-timing: pull_request_layout-fragment;desc="pull_request_layout fragment";dur=279.064008,conversation_content-fragment;desc="conversation_content fragment";dur=1001.430395,conversation_sidebar-fragment;desc="conversation_sidebar fragment";dur=320.339307,nginx;desc="NGINX";dur=0.589988,glb;desc="GLB";dur=100.508944
strict-transport-security: max-age=31536000; includeSubdomains; preload
vary: X-PJAX, X-PJAX-Container, Turbo-Visit, Turbo-Frame, X-Requested-With,Accept-Encoding, Accept, X-Requested-With
x-content-type-options: nosniff
x-frame-options: deny
x-voltron-version: a2eb102
x-xss-protection: 0
server: github.com
content-encoding: gzip
accept-ranges: bytes
set-cookie: _gh_sess=nO5BmclO%2F0UOZcN7t6xAudoPmB1bpSTA4%2BODwgXA22yqbhZOitmmTFI0AXrBJsTnaD0zncTf45p5OBDs2XZedTyGElRmWCPwPebpwqNLfYDQnJBPUyHaW1nRwIyZ4Tq7zDxjHPjFvT1fIs9IwMqlKOt3Nt%2FbHGqpkv9NPsimisTBJttLZjJA281RA9ztCrn9ep07S3hoRbinUTxOIzRPIDuW4A6cyChFFFVlWtSY9WTJJIwD1VSHZqnd%2FMOKO%2Br2ODiEjuD2ata4CyfQCPRI%2Bw%3D%3D--PpyonJRmc2OvJs7d--taH5AZpw4YBvdpRjuM0q9A%3D%3D; Path=/; HttpOnly; Secure; SameSite=Lax
set-cookie: _octo=GH1.1.10749645.1753400755; Path=/; Domain=github.com; Expires=Fri, 24 Jul 2026 23:45:55 GMT; Secure; SameSite=Lax
set-cookie: logged_in=no; Path=/; Domain=github.com; Expires=Fri, 24 Jul 2026 23:45:55 GMT; HttpOnly; Secure; SameSite=Lax
x-github-request-id: E65C:32222C:1D657:2E305:6882C5B3
Unify fused_dot_product_attention with scaled_dot_product_attention by deepllz · Pull Request #65507 · PaddlePaddle/Paddle · GitHub
deepllz
changed the title
Update cudnn flash attention
Unify fused_dot_product_attention with scaled_dot_product_attention and polish some codes
Jul 3, 2024
deepllz
changed the title
Unify fused_dot_product_attention with scaled_dot_product_attention and polish some codes
Unify fused_dot_product_attention with scaled_dot_product_attention
Jul 5, 2024
Skip to content
Navigation Menu
{{ message }}
-
Notifications
You must be signed in to change notification settings - Fork 5.8k
Unify fused_dot_product_attention with scaled_dot_product_attention #65507
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
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
fix error fix pir pass fix ci add more ut minor changes remove workspace_opt env minor change update api doc
|
你的PR提交成功，感谢你对开源项目的贡献! |
deepllz
changed the title
|
LGTM |
zhiqiu
previously approved these changes
Jul 5, 2024
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
sneaxiy
approved these changes
Jul 5, 2024
| cu_seqlen_q = None | ||
| cu_seqlen_k = None | ||
| head_dim = query.shape[3] | ||
| scaling_factor = head_dim**-0.5 |
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.
scaling_factor可以保留None的默认参数，这样以后可以给其他值。在为None的时候，自动变成head_dim**-0.5.
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.
Done
Wong4j
approved these changes
Jul 5, 2024
sneaxiy
requested changes
Jul 5, 2024
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.
请回退graph_pattern_detector.cc的改动，并给fused_dot_product_attention补回scaling_factor的参数选项。
Done |
deepllz
changed the title
sneaxiy
approved these changes
Jul 8, 2024
GuoxiaWang
pushed a commit
to GuoxiaWang/Paddle
that referenced
this pull request
Aug 29, 2024
…addlePaddle#65507) * update cudnn flash attention fix error fix pir pass fix ci add more ut minor changes remove workspace_opt env minor change update api doc * polish * fix static test * revert graph_pattern_detector.cc modify --------- Co-authored-by: Shijie Wang <jaywan@nvidia.com>
GuoxiaWang
pushed a commit
to GuoxiaWang/Paddle
that referenced
this pull request
Sep 22, 2024
…addlePaddle#65507) * update cudnn flash attention fix error fix pir pass fix ci add more ut minor changes remove workspace_opt env minor change update api doc * polish * fix static test * revert graph_pattern_detector.cc modify --------- Co-authored-by: Shijie Wang <jaywan@nvidia.com>
ForFishes
pushed a commit
that referenced
this pull request
Sep 23, 2024
* update cudnn flash attention (#63028) update cudnn flash attention * Unify fused_dot_product_attention with scaled_dot_product_attention (#65507) * update cudnn flash attention fix error fix pir pass fix ci add more ut minor changes remove workspace_opt env minor change update api doc * polish * fix static test * revert graph_pattern_detector.cc modify --------- Co-authored-by: Shijie Wang <jaywan@nvidia.com> * add hopper arch support for flash_attention * add flag PADDLE_DISABLE_CUDNN_FA to disable use cudnn fa * fix environment * fix --------- Co-authored-by: Shijie <jaywan@nvidia.com> Co-authored-by: zhengzhonghui <zhengzhonghui@baidu.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
None yet
4 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.
You can’t perform that action at this time.
PR Category
Performance Optimization
PR Types
Performance
Description
此PR继承自#63028
Hopper卡上，cudnn版本的fa，对比开源版本的fa，性能有大幅提升，对不同shape的输入进行测试，得出性能提升与head_dim正相关，不同head_dim性能提升如下：
causal_mask=True，即mask=None：
head_dim=64， forward+backward性能提升36%~45%
head_dim=128，forward+backward性能提升65%~75%
arbitraty mask：
head_dim=64， forward+backward性能提升13%~16%
head_dim=128，forward+backward性能提升1%~5%
在Ampere卡上，cudnn版本的fa对比开源版本有30%~60%的降速，后续会考虑根据架构来选择使用两个API。
由于目前此单测对卡型号以及cuda和cudnn版本有要求，所以CI中暂时未执行到此单测，一下是单测执行结果：