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

[GH-ISSUE #269] If the Ascend team integrates EP-related capabilities into DeepEP, will the community welcome it? #198

New issue
Open
opened 2026-10-26 09:56:24 +00:00 by bsakaguchi · 2 comments
bsakaguchi commented 2026-10-26 09:56:24 +00:00
Owner
Copy link

Originally created by @Yael-X on GitHub (Jun 30, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/269

Originally created by @Yael-X on GitHub (Jun 30, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/269
bsakaguchi commented 2026-10-26 09:56:26 +00:00
Author
Owner
Copy link

@LyricZhao commented on GitHub (Jul 2, 2025):

Sure! But I guess the whole repo should be refactored, as NVIDIA and Ascend devices are totally different. I guess a brand-new repo would be more appropriate 👍🏻, e.g. https://github.com/vllm-project/vllm-ascend

<!-- gh-comment-id:3026670577 --> @LyricZhao commented on GitHub (Jul 2, 2025): Sure! But I guess the whole repo should be refactored, as NVIDIA and Ascend devices are totally different. I guess a brand-new repo would be more appropriate 👍🏻, e.g. https://github.com/vllm-project/vllm-ascend
bsakaguchi commented 2026-10-26 09:56:26 +00:00
Author
Owner
Copy link

@Yael-X commented on GitHub (Jul 3, 2025):

Sure! But I guess the whole repo should be refactored, as NVIDIA and Ascend devices are totally different. I guess a brand-new repo would be more appropriate 👍🏻, e.g. https://github.com/vllm-project/vllm-ascend

Actually，We plan to develop an Ascend-optimized EP communication backend ​​with strict adherence to​​ DeepEP's core API specifications. By upstreaming this module, DeepEP ​​would​​ seamlessly extend its support to Ascend devices, allowing major users such as ByteDance and Tencent to deploy ​​a single DeepEP codebase across heterogeneous clusters​​ (NVIDIA ​​or​​ Ascend). Crucially, this ​​ensures​​ interface consistency for upper-layer frameworks (e.g., vLLM, SGLang), ​​removing​​ the need for additional adaptations and reducing ecosystem fragmentation.

<!-- gh-comment-id:3030499731 --> @Yael-X commented on GitHub (Jul 3, 2025): > Sure! But I guess the whole repo should be refactored, as NVIDIA and Ascend devices are totally different. I guess a brand-new repo would be more appropriate 👍🏻, e.g. https://github.com/vllm-project/vllm-ascend Actually，We plan to develop an Ascend-optimized EP communication backend ​​with strict adherence to​​ DeepEP's core API specifications. By upstreaming this module, DeepEP ​​would​​ seamlessly extend its support to Ascend devices, allowing major users such as ByteDance and Tencent to deploy ​​a single DeepEP codebase across heterogeneous clusters​​ (NVIDIA ​​or​​ Ascend). Crucially, this ​​ensures​​ interface consistency for upper-layer frameworks (e.g., vLLM, SGLang), ​​removing​​ the need for additional adaptations and reducing ecosystem fragmentation.
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#198
No description provided.