Skip to content

[OPs] ep_moe_expert_dispatch.cu dispatch num_experts_per_rank 5 #5890

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yuanlehome merged 1 commit into from
Jan 6, 2026
Merged

[OPs] ep_moe_expert_dispatch.cu dispatch num_experts_per_rank 5 #5890

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions custom_ops/gpu_ops/moe/ep_moe_expert_dispatch.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,11 @@
__VA_ARGS__ \
break; \
} \
case 5: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 5; \
__VA_ARGS__ \
break; \
} \
Comment on lines +41 to +45
Copy link

Copilot AI Jan 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The addition of case 5 support is implemented correctly and follows the existing pattern. However, consider adding test coverage for this new value. The existing test in tests/layers/test_ep_moe_expert_dispatch_fp8.py only tests with local_num_experts=8. It would be valuable to have parametric tests that verify the dispatch logic works correctly for the newly supported value of 5.

Copilot uses AI. Check for mistakes.
case 6: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 6; \
__VA_ARGS__ \
Expand Down
Loading