[GH-ISSUE #707] DeepEP v1 Normal mode, run test_internode RuntimeError: DeepEP error: timeout (dispatch CPU) when use NVSHMEM version >= 3.5.19 #406

Open
opened 2026-10-26 10:00:12 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @alpha-baby on GitHub (Jul 28, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/707

github.com/deepseek-ai/DeepEP@dd758caf45/csrc/kernels/legacy/ibgda_device.cuh (L81)

The main branch is missing a previous adaptation for nvshmem 3.5.19 and later versions.
PR: https://github.com/deepseek-ai/DeepEP/pull/564/changes

This causes the current main branch to hang directly in the notify_dispatch kernel when running DeepEP v1.

Originally created by @alpha-baby on GitHub (Jul 28, 2026). Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/707 https://github.com/deepseek-ai/DeepEP/blob/dd758caf451848bd150e1046af3d0a73e5fff38d/csrc/kernels/legacy/ibgda_device.cuh#L81 The main branch is missing a previous adaptation for nvshmem 3.5.19 and later versions. PR: https://github.com/deepseek-ai/DeepEP/pull/564/changes This causes the current main branch to hang directly in the `notify_dispatch` kernel when running DeepEP v1.
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
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#406
No description provided.