mirror of
https://github.com/deepseek-ai/DeepEP.git
synced 2026-11-05 00:47:32 +00:00
[PR #310] [MERGED] Fix for data error and kernel hung because of inflight rdma channel head update #515
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#515
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?
📋 Pull Request Information
Original PR: https://github.com/deepseek-ai/DeepEP/pull/310
Author: @GuangguanWang
Created: 7/17/2025
Status: ✅ Merged
Merged: 7/18/2025
Merged by: @sphish
Base:
main← Head:main📝 Commits (1)
b65b22eFix for data error and kernel hung because of inflight rdma channel head update📊 Changes
1 file changed (+20 additions, -0 deletions)
View changed files
📝
csrc/kernels/internode.cu(+20 -0)📄 Description
Fix for data error and kernel hung because of inflight rdma channel head update
When dispatch/combine, neither sender nor receiver waits for the finish of the rdma channel head update, which may result in the remaining inflight head update wqes even after the kernel finished. Once the infight wqes arrive after the rdma channel head buffer cleaning for the next round of dispatch/combine, the rdma channel head buffer will be re- written to a none-zero value. The rdma sender can reuse the data buffer before the rdma receivers consume the date buffer because of the wrong rdma channel head, cauing date error and kernel hung.
For performance considering, to overlap the inflight wqes' RTT, fix this issue by waiting for all previous inflight wqes to complete before cleaning rdma buffers in the next round of dispatch/combine.
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.