Skip to content

[Attention] Refactor CUDA attention backend selection logic #24794

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 118 commits into
base: main
Choose a base branch
from
Open

[Attention] Refactor CUDA attention backend selection logic #24794

wants to merge 118 commits into from
+1,302 −1,028

Conversation

@MatthewBonanni
Copy link
Contributor

@MatthewBonanni MatthewBonanni commented Sep 13, 2025 •
edited by github-actions bot
Loading

Purpose

CudaPlatformBase.get_attention_backend_cls has gotten complex and messy over time. This PR cleans up the logic (without changing the behavior) and standardizes the interface.

Test Plan

Test Result

Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

@mergify mergify bot added rocm Related to AMD ROCm speculative-decoding v1 tpu Related to Google TPUs labels Sep 13, 2025
@mergify
Copy link

mergify bot commented Sep 13, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @MatthewBonanni.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Sep 13, 2025
njhill
njhill reviewed Sep 13, 2025
View reviewed changes
@MatthewBonanni MatthewBonanni changed the title [Attention] Refactor CUDA attention backend selection logic [WIP][Attention] Refactor CUDA attention backend selection logic Sep 13, 2025
@MatthewBonanni MatthewBonanni changed the title [WIP][Attention] Refactor CUDA attention backend selection logic [Attention] Refactor CUDA attention backend selection logic Sep 16, 2025
@MatthewBonanni MatthewBonanni marked this pull request as ready for review September 16, 2025 13:22
@mergify mergify bot removed the needs-rebase label Sep 16, 2025
@mergify
Copy link

mergify bot commented Oct 31, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @MatthewBonanni.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Oct 31, 2025
@mergify mergify bot removed the needs-rebase label Oct 31, 2025
@MatthewBonanni
fix test
0435eca 
Signed-off-by: Matthew Bonanni <[email protected]>
@mergify
Copy link

mergify bot commented Nov 2, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @MatthewBonanni.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Nov 2, 2025
@mergify mergify bot removed the needs-rebase label Nov 2, 2025
@mergify
Copy link

mergify bot commented Nov 3, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @MatthewBonanni.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Nov 3, 2025
@mergify mergify bot removed the needs-rebase label Nov 3, 2025
LucasWilkinson
LucasWilkinson reviewed Nov 4, 2025
View reviewed changes
Copy link
Collaborator

@LucasWilkinson LucasWilkinson left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

left a few comments; we should figure out who the owner of the plugin mechanism is and figure out how to notify downstream HW plugins since I think this will affect them pretty dramatically

@MatthewBonanni
fix path
15a19d3 
Signed-off-by: Matthew Bonanni <[email protected]>
@MatthewBonanni
_get_backend_priorities return sorted list instead of dict
6515e4c 
Signed-off-by: Matthew Bonanni <[email protected]>
@MatthewBonanni
fix merge miss
0b841ff 
Signed-off-by: Matthew Bonanni <[email protected]>
@MatthewBonanni
remove get_default_block_size
69bb887 
Signed-off-by: Matthew Bonanni <[email protected]>
@MatthewBonanni
Copy link
Contributor Author

MatthewBonanni commented Nov 4, 2025

@LucasWilkinson thanks for your review! I've already notified @ILikeIneine but I'm not sure if there's anyone else we should reach out to?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@mgoin mgoin mgoin left review comments

@LucasWilkinson LucasWilkinson LucasWilkinson left review comments

@NickLucche NickLucche NickLucche left review comments

@njhill njhill njhill left review comments

@chatgpt-codex-connector chatgpt-codex-connector[bot] chatgpt-codex-connector[bot] left review comments

@ProExpertProg ProExpertProg ProExpertProg approved these changes

@gshtras gshtras Awaiting requested review from gshtras gshtras is a code owner

@jikunshang jikunshang Awaiting requested review from jikunshang jikunshang is a code owner

@bigPYJ1151 bigPYJ1151 Awaiting requested review from bigPYJ1151 bigPYJ1151 is a code owner

@tdoublep tdoublep Awaiting requested review from tdoublep tdoublep is a code owner

@benchislett benchislett Awaiting requested review from benchislett benchislett is a code owner

@luccafong luccafong Awaiting requested review from luccafong luccafong is a code owner

@WoosukKwon WoosukKwon Awaiting requested review from WoosukKwon WoosukKwon is a code owner

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat robertgshaw2-redhat is a code owner

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

@comaniac comaniac Awaiting requested review from comaniac comaniac is a code owner

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat alexm-redhat is a code owner

@zhuohan123 zhuohan123 Awaiting requested review from zhuohan123 zhuohan123 is a code owner

@youkaichao youkaichao Awaiting requested review from youkaichao youkaichao is a code owner

@sighingnow sighingnow Awaiting requested review from sighingnow sighingnow is a code owner

@tlrmchlsmth tlrmchlsmth Awaiting requested review from tlrmchlsmth tlrmchlsmth is a code owner

@yewentao256 yewentao256 Awaiting requested review from yewentao256 yewentao256 is a code owner

@ApostaC ApostaC Awaiting requested review from ApostaC ApostaC is a code owner

@DarkLight1337 DarkLight1337 Awaiting requested review from DarkLight1337 DarkLight1337 is a code owner

@simon-mo simon-mo Awaiting requested review from simon-mo simon-mo is a code owner

@aarnphm aarnphm Awaiting requested review from aarnphm

@houseroad houseroad Awaiting requested review from houseroad houseroad is a code owner

@hmellor hmellor Awaiting requested review from hmellor hmellor is a code owner

@heheda12345 heheda12345 Awaiting requested review from heheda12345 heheda12345 is a code owner

@pavanimajety pavanimajety Awaiting requested review from pavanimajety pavanimajety is a code owner

@noooop noooop Awaiting requested review from noooop

@jeejeelee jeejeelee Awaiting requested review from jeejeelee

@chaunceyjiang chaunceyjiang Awaiting requested review from chaunceyjiang

@22quinn 22quinn Awaiting requested review from 22quinn

Assignees

No one assigned

Labels

ci/build deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend gpt-oss Related to GPT-OSS models kv-connector multi-modality Related to multi-modality (#4194) new-model Requests to new models performance Performance-related issues qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm speculative-decoding structured-output tpu Related to Google TPUs v1

Projects

Structured Output
Status: No status
gpt-oss Issues & Enhancements
Status: Ready

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

7 participants

@MatthewBonanni @ILikeIneine @mgoin @LucasWilkinson @NickLucche @ProExpertProg @njhill