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

Wire up load progress #4547

Merged
merged 1 commit into from
May 23, 2024
Merged

Wire up load progress #4547

merged 1 commit into from
May 23, 2024

Conversation

dhiltgen
Copy link
Collaborator

@dhiltgen dhiltgen commented May 20, 2024

This doesn't expose a UX yet, but wires the initial server portion of progress reporting during load

TODO

  • Adjust waitUntilRunning to be smarter and look for stalled loads instead of a dumb 10m timer
  • expose progress in ollama run UX can come in a follow up PR
  • expose percent loaded in ollama ps UX can come in a follow up PR

Fixes #4350
Replaces #4123 #4419

This should provide a good balance between slow model loads vs. detecting stalls without taking too long before giving up.

This doesn't expose a UX yet, but wires the initial server portion
of progress reporting during load
@dhiltgen dhiltgen marked this pull request as ready for review May 23, 2024 20:40
@dhiltgen dhiltgen merged commit 95b1133 into ollama:main May 23, 2024
15 checks passed
@dhiltgen dhiltgen deleted the load_progress branch May 23, 2024 21:06
@UmutAlihan
Copy link

so fast progress cheers to all great contributors

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

Successfully merging this pull request may close these issues.

Configurable model loading timeout
3 participants