Support CUDA Graph for internode dispatch normal kernel #438
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
yifeizhang-c
commented
Sep 30, 2025
| while (ld_volatile_global(moe_recv_rdma_counter_mapped) != -1); | ||
| *moe_recv_rdma_counter_mapped = sum; | ||
| if (num_worst_tokens == 0) { | ||
| while (ld_volatile_global(moe_recv_rdma_counter_mapped) != -1); |
There was a problem hiding this comment.
I wish to double confirm the design here. Is the while (ld_volatile_global(...)) logic here aiming for cache coherency? That device side need to check whether the host side value update has already been written back before device side make the update.
I wish to confirm this because intranode dispatch does not have such logic.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support CUDA Graph for internode dispatch kernels with the same logic as what has been done for intranode dispatch kernels.