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 #140] internode_combine Timeout Errors in C++ Library Integration​ #123

New issue
Closed
opened 2026-10-26 09:54:47 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-26 09:54:47 +00:00
Owner
Copy link

Originally created by @duzeyan on GitHub (Apr 28, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/140

this project is Excellent. After removing the Python interface and rebuilding a C++ library for integration, we encountered the following timeout errors during testing with internode_combine

DeepEP combine RDMA receiver timeout, channel: 0, RDMA: 0, nvl: 0, src RDMA: 0, tail: 0, waiting: 0, expect: 0
DeepEP combine RDMA receiver timeout, channel: 0, RDMA: 0, nvl: 0, src RDMA: 1, tail: 0, waiting: 0, expect: 0
DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 0, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0
DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 1, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0
DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 6, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0
...
...

Any suggestions on debugging or potential missing configurations would be appreciated.

Originally created by @duzeyan on GitHub (Apr 28, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/140 this project is Excellent. After removing the Python interface and rebuilding a C++ library for integration, we encountered the following timeout errors during testing with internode_combine ``` DeepEP combine RDMA receiver timeout, channel: 0, RDMA: 0, nvl: 0, src RDMA: 0, tail: 0, waiting: 0, expect: 0 DeepEP combine RDMA receiver timeout, channel: 0, RDMA: 0, nvl: 0, src RDMA: 1, tail: 0, waiting: 0, expect: 0 DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 0, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0 DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 1, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0 DeepEP combine forwarder (NVL check) timeout, channel: 0, RDMA: 0, nvl: 0, src NVL: 6, dst RDMA: 1, tail: 0, waiting: 0, total: 1, sub: 0, large: 8, expected: 0 ... ... ``` Any suggestions on debugging or potential missing configurations would be appreciated.
bsakaguchi commented 2026-10-26 09:54:49 +00:00
Author
Owner
Copy link

@duzeyan commented on GitHub (Apr 28, 2025):

fixed .
mixed up 'recv_gbl_channel_prefix_matrix' with 'gbl_channel_prefix_matrix'."

<!-- gh-comment-id:2834654153 --> @duzeyan commented on GitHub (Apr 28, 2025): fixed . mixed up 'recv_gbl_channel_prefix_matrix' with 'gbl_channel_prefix_matrix'."
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#123
No description provided.