deepseek-ai/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM.git synced 2026-11-05 00:47:26 +00:00
Code Issues 162 Projects Packages Wiki Activity

[GH-ISSUE #59] [Question] Why not use TMA to load RHS scales? #38

New issue
Closed
opened 2026-10-26 21:11:02 +00:00 by bsakaguchi · 2 comments
bsakaguchi commented 2026-10-26 21:11:02 +00:00
Owner
Copy link

Originally created by @ZJUGuoShuai on GitHub (Mar 12, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/59

The implementation uses TMA to load for LHS, LHS scaling factors, and RHS matrices. Why not use TMA to load RHS scales? Is it just for overlapping it with the TMA store in Math Warp-Groups?

Originally created by @ZJUGuoShuai on GitHub (Mar 12, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/59 The implementation uses TMA to load for LHS, LHS scaling factors, and RHS matrices. Why not use TMA to load RHS scales? Is it just for overlapping it with the TMA store in Math Warp-Groups?
bsakaguchi commented 2026-10-26 21:11:03 +00:00
Author
Owner
Copy link

@soundOfDestiny commented on GitHub (Mar 13, 2025):

It's okay to use TMA to load RHS scales.

<!-- gh-comment-id:2719713342 --> @soundOfDestiny commented on GitHub (Mar 13, 2025): It's okay to use TMA to load RHS scales.
bsakaguchi commented 2026-10-26 21:11:03 +00:00
Author
Owner
Copy link

@soundOfDestiny commented on GitHub (Mar 16, 2025):

example:
github.com/ademeure/DeeperGEMM@d1e54c9633
Thanks @ademeure

<!-- gh-comment-id:2727222014 --> @soundOfDestiny commented on GitHub (Mar 16, 2025): example: https://github.com/ademeure/DeeperGEMM/commit/d1e54c9633c4a9d4e2aa849aec7275aafd949b24 Thanks @ademeure
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
public-sync-20261014
0930-release
nv_dev
fix-mega-moe-fence
public-release-2609
public-release-2607
public-release-2606
mega-update
public-release-260416
ko3n1g/ci/build-wheels
nv_dev_f8e8fb5
nv_dev_950d31a
nv_dev_67fc648
nv_dev_c491439
nv_dev_4ff3f54
v2.1.1.post3
v2.1.1.post2
v2.1.1.post1
v2.1.1
v2.1.0
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepGEMM#38
No description provided.