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 #439] [MERGED] Add permute extension to hybrid-ep #573

New issue
Closed
opened 2026-10-27 21:04:10 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-27 21:04:10 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/439
Author: @Autumn1998
Created: 9/30/2025
Status: ✅ Merged
Merged: 10/9/2025
Merged by: @jershi425

Base: hybrid-ep ← Head: mcore_dev

📝 Commits (1)

  • 0641c08 add permute/unpermute, add sync free, refactor

📊 Changes

14 files changed (+1903 additions, -681 deletions)

View changed files

📝 Hybrid-EP_Intra-node_Implementation.md (+24 -34)
➕ csrc/hybrid_ep/executor/executor.cu (+299 -0)
➕ csrc/hybrid_ep/executor/executor.cuh (+96 -0)
➕ csrc/hybrid_ep/extension/permute.cu (+626 -0)
➕ csrc/hybrid_ep/extension/permute.cuh (+117 -0)
📝 csrc/hybrid_ep/hybrid_ep.cu (+189 -289)
📝 csrc/hybrid_ep/hybrid_ep.cuh (+38 -51)
📝 csrc/hybrid_ep/pybind_hybrid_ep.cu (+21 -6)
📝 csrc/hybrid_ep/utils.cuh (+37 -0)
📝 deep_ep/hybrid_ep_buffer.py (+210 -30)
📝 setup.py (+2 -0)
📝 tests/test_hybrid_ep.py (+137 -51)
➖ tests/test_normal_without_nvl.py (+0 -220)
📝 tests/utils.py (+107 -0)

📄 Description

  1. Refine Document
  2. Add permute/unpermute to hide the D2D copy
  3. Add support for the sync-free mode

🔄 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/439 **Author:** [@Autumn1998](https://github.com/Autumn1998) **Created:** 9/30/2025 **Status:** ✅ Merged **Merged:** 10/9/2025 **Merged by:** [@jershi425](https://github.com/jershi425) **Base:** `hybrid-ep` ← **Head:** `mcore_dev` --- ### 📝 Commits (1) - [`0641c08`](https://github.com/deepseek-ai/DeepEP/commit/0641c08b43a9b7cf481c36d10e2b123a348e4489) add permute/unpermute, add sync free, refactor ### 📊 Changes **14 files changed** (+1903 additions, -681 deletions) <details> <summary>View changed files</summary> 📝 `Hybrid-EP_Intra-node_Implementation.md` (+24 -34) ➕ `csrc/hybrid_ep/executor/executor.cu` (+299 -0) ➕ `csrc/hybrid_ep/executor/executor.cuh` (+96 -0) ➕ `csrc/hybrid_ep/extension/permute.cu` (+626 -0) ➕ `csrc/hybrid_ep/extension/permute.cuh` (+117 -0) 📝 `csrc/hybrid_ep/hybrid_ep.cu` (+189 -289) 📝 `csrc/hybrid_ep/hybrid_ep.cuh` (+38 -51) 📝 `csrc/hybrid_ep/pybind_hybrid_ep.cu` (+21 -6) 📝 `csrc/hybrid_ep/utils.cuh` (+37 -0) 📝 `deep_ep/hybrid_ep_buffer.py` (+210 -30) 📝 `setup.py` (+2 -0) 📝 `tests/test_hybrid_ep.py` (+137 -51) ➖ `tests/test_normal_without_nvl.py` (+0 -220) 📝 `tests/utils.py` (+107 -0) </details> ### 📄 Description 1. Refine Document 2. Add permute/unpermute to hide the D2D copy 3. Add support for the sync-free mode --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-10-27 21:04:10 +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#573
No description provided.