[PR #204] [MERGED] Support Ampere architecture #462

Closed
opened 2026-10-26 10:01:02 +00:00 by bsakaguchi · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/204
Author: @LyricZhao
Created: 6/11/2025
Status: ✅ Merged
Merged: 6/11/2025
Merged by: @LyricZhao

Base: main ← Head: ampere-support


📝 Commits (10+)

📊 Changes

16 files changed (+413 additions, -174 deletions)

View changed files

📝 README.md (+16 -4)
📝 csrc/config.hpp (+6 -0)
📝 csrc/deep_ep.cpp (+63 -9)
📝 csrc/kernels/CMakeLists.txt (+3 -2)
📝 csrc/kernels/api.cuh (+11 -6)
📝 csrc/kernels/configs.cuh (+15 -1)
📝 csrc/kernels/internode.cu (+0 -125)
📝 csrc/kernels/intranode.cu (+25 -4)
📝 csrc/kernels/launch.cuh (+31 -0)
➕ csrc/kernels/layout.cu (+136 -0)
📝 csrc/kernels/runtime.cu (+5 -0)
📝 csrc/kernels/utils.cuh (+5 -0)
📝 deep_ep/buffer.py (+6 -1)
📝 deep_ep/utils.py (+28 -0)
📝 setup.py (+58 -16)
📝 tests/test_intranode.py (+5 -6)

📄 Description

Please notice that this support is for intranode only.


🔄 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/204 **Author:** [@LyricZhao](https://github.com/LyricZhao) **Created:** 6/11/2025 **Status:** ✅ Merged **Merged:** 6/11/2025 **Merged by:** [@LyricZhao](https://github.com/LyricZhao) **Base:** `main` ← **Head:** `ampere-support` --- ### 📝 Commits (10+) - [`d5664f3`](https://github.com/deepseek-ai/DeepEP/commit/d5664f38d56b57a957e92431906f02256b393a2d) Update README - [`5e35592`](https://github.com/deepseek-ai/DeepEP/commit/5e3559296b2059012b2f8982746ac2642eeacc6c) Update `setup.py` - [`d3ae62d`](https://github.com/deepseek-ai/DeepEP/commit/d3ae62d9efd0c464ee2d943d62182aeccc80c6d2) Fix headers - [`36fac36`](https://github.com/deepseek-ai/DeepEP/commit/36fac363b3f4d2b1bbec5dafcdc46dc4c2bb0d65) Add `DISABLE_NVSHMEM` for APIs - [`7635af2`](https://github.com/deepseek-ai/DeepEP/commit/7635af2073a24eea077c8d18334f477280ba976f) Fix launch - [`910c338`](https://github.com/deepseek-ai/DeepEP/commit/910c338a7135b2e293626e5bb7b38bc91a3b116e) Fix TMA settings - [`422e2a3`](https://github.com/deepseek-ai/DeepEP/commit/422e2a3c64ac445e62bb76bf51d48a4f04b87ed8) Fix TMA usages - [`d2ca520`](https://github.com/deepseek-ai/DeepEP/commit/d2ca520b8fc3c4e608bc0e53d75f28eb81b8b725) Fix dlink - [`1204a56`](https://github.com/deepseek-ai/DeepEP/commit/1204a563dd300bb02d46b4a2180deecb01d2f0bc) Separate layout kernels - [`4664e83`](https://github.com/deepseek-ai/DeepEP/commit/4664e83779e4368005251b09b1ccd34dcc072264) Update version ### 📊 Changes **16 files changed** (+413 additions, -174 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+16 -4) 📝 `csrc/config.hpp` (+6 -0) 📝 `csrc/deep_ep.cpp` (+63 -9) 📝 `csrc/kernels/CMakeLists.txt` (+3 -2) 📝 `csrc/kernels/api.cuh` (+11 -6) 📝 `csrc/kernels/configs.cuh` (+15 -1) 📝 `csrc/kernels/internode.cu` (+0 -125) 📝 `csrc/kernels/intranode.cu` (+25 -4) 📝 `csrc/kernels/launch.cuh` (+31 -0) ➕ `csrc/kernels/layout.cu` (+136 -0) 📝 `csrc/kernels/runtime.cu` (+5 -0) 📝 `csrc/kernels/utils.cuh` (+5 -0) 📝 `deep_ep/buffer.py` (+6 -1) 📝 `deep_ep/utils.py` (+28 -0) 📝 `setup.py` (+58 -16) 📝 `tests/test_intranode.py` (+5 -6) </details> ### 📄 Description Please notice that this support is for intranode only. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-10-26 10:01:02 +00:00
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
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#462
No description provided.