8000 Support for concurrent requests with LM Studio server · Issue #259 · lmstudio-ai/lms · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
Support for concurrent requests with LM Studio server #259
Open
@siddhantpathakk

Description

@siddhantpathakk

I am building an AI applicatiom where I would like to host the LLM on my own Mac Studio using LM Studio as an OpenAI-compatible endpoint and MLX as backend

I use the "lms server start" command to run it on my machine.

It works, but I just have one question- does LM studio have any support for concurrency- like what if I get 3 requests together - how does that handling work?

Will they all just fall in some sort of “queue” where request get processed sequentially?

Or

If there is enough space in the RAM -> it will be able to handle multiple requests concurrently?

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

      0