[PR #218] Support other NVLink scenarios #474

New issue

Open

opened 2026-10-26 10:01:10 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 10:01:10 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/218
Author: @fzyzcjy
Created: 6/17/2025
Status: 🔄 Open

Base: main ← Head: feat/deepep_normal_update

📝 Commits (10+)

be2eed8 more
9ecb941 more
9683d94 more
8cf6bd8 more
acf108a more
3e2cede Revert "more"
45fa1af Revert "more"
443bfa8 more
b986cce more
3ea6f58 more

📊 Changes

10 files changed (+248 additions, -21 deletions)

View changed files

📝 csrc/deep_ep.cpp (+135 -9)
📝 csrc/deep_ep.hpp (+33 -1)
📝 csrc/kernels/configs.cuh (+7 -0)
📝 csrc/kernels/exception.cuh (+12 -0)
📝 csrc/kernels/internode.cu (+6 -0)
📝 csrc/kernels/launch.cuh (+2 -0)
📝 csrc/kernels/layout.cu (+33 -2)
📝 setup.py (+1 -1)
📝 tests/test_intranode.py (+16 -7)
📝 tests/utils.py (+3 -1)

📄 Description

test with 4 rank, 8 rank, 24 rank all pass. code is messy and I will refactor later, and also will try to improve a bit of performance if possible.

Please subtract code diff from https://github.com/deepseek-ai/DeepEP/pull/217.

_{🔄 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/218 **Author:** [@fzyzcjy](https://github.com/fzyzcjy) **Created:** 6/17/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feat/deepep_normal_update` --- ### 📝 Commits (10+) - [`be2eed8`](https://github.com/deepseek-ai/DeepEP/commit/be2eed8f6c40e67f17f0dd9335d6ddb113713af4) more - [`9ecb941`](https://github.com/deepseek-ai/DeepEP/commit/9ecb9411c719badba8814cb92f9d4bf2331f0a87) more - [`9683d94`](https://github.com/deepseek-ai/DeepEP/commit/9683d9453ed9132b288c46b4232067707db29a49) more - [`8cf6bd8`](https://github.com/deepseek-ai/DeepEP/commit/8cf6bd88ea51f993da7a177c27826c91111de7c9) more - [`acf108a`](https://github.com/deepseek-ai/DeepEP/commit/acf108ab4818d306fe973a010db6b76de40ef17d) more - [`3e2cede`](https://github.com/deepseek-ai/DeepEP/commit/3e2cede81cf741c6867af3f97f36a9af943c8d71) Revert "more" - [`45fa1af`](https://github.com/deepseek-ai/DeepEP/commit/45fa1af2428c56b2a2ec6df3b28904c687003e71) Revert "more" - [`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 ### 📊 Changes **10 files changed** (+248 additions, -21 deletions) <details> <summary>View changed files</summary> 📝 `csrc/deep_ep.cpp` (+135 -9) 📝 `csrc/deep_ep.hpp` (+33 -1) 📝 `csrc/kernels/configs.cuh` (+7 -0) 📝 `csrc/kernels/exception.cuh` (+12 -0) 📝 `csrc/kernels/internode.cu` (+6 -0) 📝 `csrc/kernels/launch.cuh` (+2 -0) 📝 `csrc/kernels/layout.cu` (+33 -2) 📝 `setup.py` (+1 -1) 📝 `tests/test_intranode.py` (+16 -7) 📝 `tests/utils.py` (+3 -1) </details> ### 📄 Description test with 4 rank, 8 rank, 24 rank all pass. code is messy and I will refactor later, and also will try to improve a bit of performance if possible. Please subtract code diff from https://github.com/deepseek-ai/DeepEP/pull/217. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi added the

pull-request

label

2026-10-26 10:01:10 +00:00

bsakaguchi referenced this issue

2026-10-27 21:04:21 +00:00

[PR #474] [CLOSED] Add RDMA support for hybrid-EP #591