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

planning: Cortex.cpp features needed to fully support Jan #1555

Closed
gabrielle-ong opened this issue Oct 25, 2024 · 1 comment
Closed

planning: Cortex.cpp features needed to fully support Jan #1555

gabrielle-ong opened this issue Oct 25, 2024 · 1 comment
Labels
type: planning Opening up a discussion

Comments

@gabrielle-ong
Copy link
Contributor

gabrielle-ong commented Oct 25, 2024

WIP list

Model Hub

  • Updated models, delist
  • Jan dogfoods this to display on UI
  • future: eg Cortex remote models list

View RAM, CPU usage

  • requires reimplementing cortex ps for each engine
  • Can be deployed first but currently combines all engines together resulting in inaccurate

Hardware, eg GPU support

Support Tensorrt-llm engines [Prioritised?]

  • Need to define Model artifact, model.yml
  • need to bundle artifacts (needs investigating)

multi-modal - cortex.cpp needs to be able to pull 2 models at the same time

  • Need to define model.yml for the models

To add (priority, needed, blockers, effort)

@gabrielle-ong gabrielle-ong added type: epic A major feature or initiative type: planning Opening up a discussion and removed type: epic A major feature or initiative labels Oct 25, 2024
@gabrielle-ong
Copy link
Contributor Author

Closing in favour of Jan issues

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type: planning Opening up a discussion
Projects
Status: Completed
Development

No branches or pull requests

1 participant