Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature Request: Multi session chat support #7758

Open
4 tasks done
BigCatGit opened this issue Jun 5, 2024 · 3 comments
Open
4 tasks done

Feature Request: Multi session chat support #7758

BigCatGit opened this issue Jun 5, 2024 · 3 comments
Labels
enhancement New feature or request

Comments

@BigCatGit
Copy link

Prerequisites

  • I am running the latest code. Mention the version if possible as well.
  • I carefully followed the README.md.
  • I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

After running the llama3 model and using curl for simultaneous conversations, I received responses that were queued instead of running simultaneously. I hope to support the processing of multiple sessions like multithreading

Motivation

Implement local multi session chat

Possible Implementation

No response

@BigCatGit BigCatGit added the enhancement New feature or request label Jun 5, 2024
@HanClinto
Copy link
Collaborator

See #5762 and #4216 for more discussion of (possibly-related) server improvements.

@HanClinto
Copy link
Collaborator

HanClinto commented Jun 5, 2024

Looking at #5794 it appears that this feature may already be added.

When running the server, did you set the --threads-http parameter? Setting this to >1 looks like it may enable you to process multiple requests simultaneously? (disclaimer: I have not yet attempted this myself, so please let me know if I misunderstood your report, your request, or the current server capabilities)

@person4268
Copy link

person4268 commented Jun 7, 2024

Try setting --cont-batching and --parallel 2. (edit: looks like --cont-batching is already enabled by default, so you should just need to set --parallel?)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants