deepseek-ai/DeepEP
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepEP.git synced 2026-11-05 00:47:32 +00:00
Code Issues 308 Projects Packages Wiki Activity

[PR #299] [MERGED] Optimize low latency combine send with TMA #508

New issue
Closed
opened 2026-10-27 21:03:23 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-27 21:03:23 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/299
Author: @zheanxu
Created: 7/14/2025
Status: ✅ Merged
Merged: 7/14/2025
Merged by: @LyricZhao

Base: main ← Head: ll-tma-inplace

📝 Commits (5)

  • 9051080 feat: low latency combine inplace TMA
  • dbd5178 optimize tma pointer with PatternVisitor
  • 5a70fb9 Merge branch 'main' into ll-tma-inplace
  • 785a9d7 Minor cleanup
  • d0a0cb1 Add elect_one_sync

📊 Changes

2 files changed (+116 additions, -26 deletions)

View changed files

📝 csrc/kernels/internode_ll.cu (+84 -26)
📝 csrc/kernels/utils.cuh (+32 -0)

📄 Description

No description provided

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepEP/pull/299 **Author:** [@zheanxu](https://github.com/zheanxu) **Created:** 7/14/2025 **Status:** ✅ Merged **Merged:** 7/14/2025 **Merged by:** [@LyricZhao](https://github.com/LyricZhao) **Base:** `main` ← **Head:** `ll-tma-inplace` --- ### 📝 Commits (5) - [`9051080`](https://github.com/deepseek-ai/DeepEP/commit/90510804cb1d630b5383b62bff3316e88c1c49f0) feat: low latency combine inplace TMA - [`dbd5178`](https://github.com/deepseek-ai/DeepEP/commit/dbd5178a94b71e758aef15be7c65bcbff5e340fe) optimize tma pointer with PatternVisitor - [`5a70fb9`](https://github.com/deepseek-ai/DeepEP/commit/5a70fb9e1904bcbdc62d24729d4a8ff34fe28128) Merge branch 'main' into ll-tma-inplace - [`785a9d7`](https://github.com/deepseek-ai/DeepEP/commit/785a9d7299577f65abc6babf602040973c0178fd) Minor cleanup - [`d0a0cb1`](https://github.com/deepseek-ai/DeepEP/commit/d0a0cb1bc470fdaa65de090868680697ef01dc50) Add `elect_one_sync` ### 📊 Changes **2 files changed** (+116 additions, -26 deletions) <details> <summary>View changed files</summary> 📝 `csrc/kernels/internode_ll.cu` (+84 -26) 📝 `csrc/kernels/utils.cuh` (+32 -0) </details> ### 📄 Description _No description provided_ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-10-27 21:03:23 +00:00
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
hybrid-ep
chore/remove-clang-format-yapf
v2.5
nvDev
try-fix-cu128
mori-ep
antgroup-opt
compat-old-torch
add-linter
eager-rdma
v1.2.1
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/DeepEP#508
No description provided.