Skip to content

[Bug]: [ERROR]Fail to bind embedding model: NCCL Error 2: unhandled system error (run with NCCL_DEBUG=INFO for details) #6170

@liuxc1

Description

@liuxc1

Self Checks

  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (Language Policy).
  • Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
  • Please do not modify this template :) and fill in all the required fields.

RAGFlow workspace code commit ID

0.17.0

RAGFlow image version

0.17.0

Other environment information

Actual behavior

使用docker部署时,启用多个解析线程。宿主机为多网卡时产生如下异常。
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/

PY=python3
if [[ -z "$WS" || $WS -lt 1 ]]; then
WS=5
fi

[ERROR]Fail to bind embedding model: NCCL Error 2: unhandled system error (run with NCCL_DEBUG=INFO for details)

Expected behavior

No response

Steps to reproduce

使用docker部署时,启用多个解析线程。宿主机为多网卡时产生如下异常。
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/

PY=python3
if [[ -z "$WS" || $WS -lt 1 ]]; then
  WS=5
fi

[ERROR]Fail to bind embedding model: NCCL Error 2: unhandled system error (run with NCCL_DEBUG=INFO for details)

Additional information

No response

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