Skip to content

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

Open
Open
DeepEP v1 Normal mode, run test_internode RuntimeError: DeepEP error: timeout (dispatch CPU) when use NVSHMEM version >= 3.5.19#707

Description

@alpha-baby
alpha-baby
opened on Jul 28, 2026

DeepEP/csrc/kernels/legacy/ibgda_device.cuh

Line 81 in dd758ca

__device__ static __forceinline__ nvshmemi_ibgda_device_qp_t* ibgda_get_rc(int pe, int id) {

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.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions