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 #416] Support per tensor transfer #560

New issue
Open
opened 2026-10-27 21:04:02 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-27 21:04:02 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/416
Author: @ayrnb
Created: 9/18/2025
Status: 🔄 Open

Base: main ← Head: support_per_tensor_transfer

📝 Commits (5)

📊 Changes

5 files changed (+86 additions, -36 deletions)

View changed files

📝 csrc/deep_ep.cpp (+20 -4)
📝 csrc/deep_ep.hpp (+3 -1)
📝 csrc/kernels/api.cuh (+14 -0)
📝 csrc/kernels/internode_ll.cu (+42 -29)
📝 deep_ep/buffer.py (+7 -2)

📄 Description

sglang w4afp8 https://github.com/sgl-project/sglang/pull/7762 is static per tensor quantization, so static per tensor quantization is added in ll dispatch.

🔄 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/416 **Author:** [@ayrnb](https://github.com/ayrnb) **Created:** 9/18/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `support_per_tensor_transfer` --- ### 📝 Commits (5) - [`b8c76b6`](https://github.com/deepseek-ai/DeepEP/commit/b8c76b68f74a4c3aa435ecec8a3701e0057f297f) support per tensor - [`8505753`](https://github.com/deepseek-ai/DeepEP/commit/850575359e3d22a5926d12c218f21195a831945b) bugfix - [`2df3680`](https://github.com/deepseek-ai/DeepEP/commit/2df3680e42e933bdd827e86cc6e4abb52e94caf3) bugfix - [`cb8096b`](https://github.com/deepseek-ai/DeepEP/commit/cb8096ba01e92b9643cc791e523872551cda15a8) fix - [`dcfd954`](https://github.com/deepseek-ai/DeepEP/commit/dcfd954851157f0bf683e1c3f1a7778f78344759) clean code ### 📊 Changes **5 files changed** (+86 additions, -36 deletions) <details> <summary>View changed files</summary> 📝 `csrc/deep_ep.cpp` (+20 -4) 📝 `csrc/deep_ep.hpp` (+3 -1) 📝 `csrc/kernels/api.cuh` (+14 -0) 📝 `csrc/kernels/internode_ll.cu` (+42 -29) 📝 `deep_ep/buffer.py` (+7 -2) </details> ### 📄 Description sglang w4afp8 https://github.com/sgl-project/sglang/pull/7762 is static per tensor quantization, so static per tensor quantization is added in ll dispatch. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
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#560
No description provided.