Skip to content

[Feature] pytorch backend 的embedding 层支持tp并行 #4243

@Tsundoku958

Description

@Tsundoku958

Motivation

lmdeploy pytorch backend的embedding层似乎没有实现tp并行,但embedding层和linear层一样同属模型参数的主要组成部分,显存占用较大,lmdeploy有计划支持embedding层的tp并行吗

Related resources

No response

Additional context

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