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 #389] [bug] kNumExpertsPerSM = 4 cause hung on H20 #262

New issue
Open
opened 2026-10-26 09:57:36 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-26 09:57:36 +00:00
Owner
Copy link

Originally created by @gangxie112 on GitHub (Sep 2, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/389

Hello,

Recently, we are trying to run deepep on some H20s and it always hung after some steps with recent commit (no such issue on older version, like before June 2nd). So we revert the commit one by one and reproduce this issue. Finally, we found it's github.com/deepseek-ai/DeepEP@d4f3497 which introduced the issue:
constexpr int kNumThreads = 256, kNumExpertsPerSM = 32, kNumRanksPerSM = 8; => constexpr int kNumThreads = 256, kNumExpertsPerSM = 4, kNumRanksPerSM = 8;

Not sure why this happen. Anyone hit this issue?

Thanks,

Originally created by @gangxie112 on GitHub (Sep 2, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/389 Hello, Recently, we are trying to run deepep on some H20s and it always hung after some steps with recent commit (no such issue on older version, like before June 2nd). So we revert the commit one by one and reproduce this issue. Finally, we found it's https://github.com/deepseek-ai/DeepEP/commit/d4f3497 which introduced the issue: `constexpr int kNumThreads = 256, kNumExpertsPerSM = 32, kNumRanksPerSM = 8;` => `constexpr int kNumThreads = 256, kNumExpertsPerSM = 4, kNumRanksPerSM = 8;` Not sure why this happen. Anyone hit this issue? Thanks,
bsakaguchi commented 2026-10-26 09:57:38 +00:00
Author
Owner
Copy link

@acelyc111 commented on GitHub (Sep 8, 2025):

@LyricZhao Which GPU dose this commit aim to optimize? H20 has only 78 SMs, is it more likely to trigger this hung issue?

<!-- gh-comment-id:3264443677 --> @acelyc111 commented on GitHub (Sep 8, 2025): @LyricZhao Which GPU dose this commit aim to optimize? H20 has only 78 SMs, is it more likely to trigger this hung issue?
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#262
No description provided.