Skip to content

为什么说“当前Inference场景中,无论用户直接使用TFServing还是使用TF提供的C++接口调用Session::Run,都无法实现多个Session并发处理Request” #1009

@Nov11

Description

@Nov11

The DeepRec docs are open source! To get involved, read the user documents: https://deeprec.readthedocs.io/en/latest/index.html

URL(s) with the issue

Description of issue (what needs changing)

如题, 文档里看到这句话, 是指Session::Run内部有锁之类的操作, 使得统一时刻发出的多个Session::Run调用必须排队吗?

求指明什么地方有这种限制,看了半天tf代码没发现不对劲的地方🤦

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions