mirror of
https://github.com/deepseek-ai/DeepEP.git
synced 2026-11-05 00:47:32 +00:00
[GH-ISSUE #144] Profiling Results on H20 with DSv3 #126
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepEP#126
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @hpz4311 on GitHub (Apr 29, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/144
Issue:
During profiling on H20 (DSv3), we observed that the time spent in both the dispatch and combine operations (specifically the notify interface called before these steps) is significantly longer than the actual communication time. These two kernels appear to be causing the total communication time in DeepEP to nearly double.
Question:
Is this an expected behavior, or could it be due to incorrect usage on our side?
@hpz4311 commented on GitHub (Apr 29, 2025):