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 #405] One branch that contains several optimizations and features #551

New issue
Open
opened 2026-10-27 21:03:58 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-27 21:03:58 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/405
Author: @fzyzcjy
Created: 9/15/2025
Status: 🔄 Open

Base: main ← Head: feat/dev_20250914

📝 Commits (10+)

📊 Changes

11 files changed (+1488 additions, -62 deletions)

View changed files

📝 csrc/deep_ep.cpp (+175 -13)
📝 csrc/deep_ep.hpp (+34 -2)
📝 csrc/kernels/api.cuh (+4 -1)
📝 csrc/kernels/exception.cuh (+12 -0)
📝 csrc/kernels/internode_ll.cu (+749 -15)
📝 csrc/kernels/utils.cuh (+18 -0)
📝 deep_ep/buffer.py (+21 -5)
📝 setup.py (+1 -1)
📝 tests/test_low_latency.py (+135 -22)
➕ tests/test_low_latency_fp4.py (+206 -0)
📝 tests/utils.py (+133 -3)

📄 Description

before each one is merged, here is a temporary unified branch

🔄 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/405 **Author:** [@fzyzcjy](https://github.com/fzyzcjy) **Created:** 9/15/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feat/dev_20250914` --- ### 📝 Commits (10+) - [`443bfa8`](https://github.com/deepseek-ai/DeepEP/commit/443bfa8692c945539bec21e2b910fc22f67f7bc0) more - [`b986cce`](https://github.com/deepseek-ai/DeepEP/commit/b986cce27bf39167488415fefcf0ee2dfee24e0c) more - [`3ea6f58`](https://github.com/deepseek-ai/DeepEP/commit/3ea6f58265cfccec4112bc00a195458dda5503d5) more - [`5d3513b`](https://github.com/deepseek-ai/DeepEP/commit/5d3513bbd3fda45cbd83b40214ecaa736267f4f0) more - [`bda5695`](https://github.com/deepseek-ai/DeepEP/commit/bda56951540b9ea4b7c110e27bb6f877cc69786b) more - [`3740762`](https://github.com/deepseek-ai/DeepEP/commit/3740762ccfe54edc147472c7c6af81196cfb1243) more - [`ad4aee8`](https://github.com/deepseek-ai/DeepEP/commit/ad4aee8bfcaa3b6c02c0eda2ec5affb637574722) more - [`b5e4aad`](https://github.com/deepseek-ai/DeepEP/commit/b5e4aad6597e7d3487718a05bfd74dac1c7e3687) more - [`240d058`](https://github.com/deepseek-ai/DeepEP/commit/240d0582533b6b0b3864f1a9835e2596bd9fc2cd) more - [`5379d59`](https://github.com/deepseek-ai/DeepEP/commit/5379d59f6889acdb2063df8177165c282348b4a1) more ### 📊 Changes **11 files changed** (+1488 additions, -62 deletions) <details> <summary>View changed files</summary> 📝 `csrc/deep_ep.cpp` (+175 -13) 📝 `csrc/deep_ep.hpp` (+34 -2) 📝 `csrc/kernels/api.cuh` (+4 -1) 📝 `csrc/kernels/exception.cuh` (+12 -0) 📝 `csrc/kernels/internode_ll.cu` (+749 -15) 📝 `csrc/kernels/utils.cuh` (+18 -0) 📝 `deep_ep/buffer.py` (+21 -5) 📝 `setup.py` (+1 -1) 📝 `tests/test_low_latency.py` (+135 -22) ➕ `tests/test_low_latency_fp4.py` (+206 -0) 📝 `tests/utils.py` (+133 -3) </details> ### 📄 Description * part of fine grained overlapping * shifang's #341 * https://github.com/deepseek-ai/DeepEP/pull/217 before each one is merged, here is a temporary unified branch --- <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#551
No description provided.