[GH-ISSUE #1291] ollama runpod serverless template #26427

Closed
opened 2026-04-22 02:43:24 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @devsaturn on GitHub (Nov 27, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1291

is there an example of deploy a model using an ollama in a runpod serverless ?

Originally created by @devsaturn on GitHub (Nov 27, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1291 is there an example of deploy a model using an ollama in a runpod serverless ?
Author
Owner

@pooyahrtn commented on GitHub (Nov 28, 2023):

@devsaturn I created this blog about doing that.

<!-- gh-comment-id:1830924185 --> @pooyahrtn commented on GitHub (Nov 28, 2023): @devsaturn I created [this](https://medium.com/@pooya.haratian/running-ollama-with-runpod-serverless-and-langchain-6657763f400d) blog about doing that.
Author
Owner

@devsaturn commented on GitHub (Nov 29, 2023):

thank you for your article which really helped me . But cold start is very slow, it downloads the manifest at each request.

<!-- gh-comment-id:1832512465 --> @devsaturn commented on GitHub (Nov 29, 2023): thank you for your article which really helped me . But cold start is very slow, it downloads the manifest at each request.
Author
Owner

@pooyahrtn commented on GitHub (Nov 29, 2023):

thank you for your article which really helped me . But cold start is very slow, it downloads the manifest at each request.

@devsaturn glad to hear. That’s true, however, with their “FlashBoot” option on, I found consecutive requests pretty fast.

<!-- gh-comment-id:1832732779 --> @pooyahrtn commented on GitHub (Nov 29, 2023): > thank you for your article which really helped me . But cold start is very slow, it downloads the manifest at each request. @devsaturn glad to hear. That’s true, however, with their “FlashBoot” option on, I found consecutive requests pretty fast.
Author
Owner

@devsaturn commented on GitHub (Dec 1, 2023):

@pooyahrtn yep very fast! do you have a stream version ?

<!-- gh-comment-id:1836860164 --> @devsaturn commented on GitHub (Dec 1, 2023): @pooyahrtn yep very fast! do you have a stream version ?
Author
Owner

@devsaturn commented on GitHub (Dec 2, 2023):

@pooyahrtn can we caching model in volume to improve model loading ?

<!-- gh-comment-id:1837108298 --> @devsaturn commented on GitHub (Dec 2, 2023): @pooyahrtn can we caching model in volume to improve model loading ?
Author
Owner

@devsaturn commented on GitHub (Dec 4, 2023):

@pooyahrtn i get sometime this error: OCI runtime pause failed: unable to freeze: unknown

<!-- gh-comment-id:1839472532 --> @devsaturn commented on GitHub (Dec 4, 2023): @pooyahrtn i get sometime this error: OCI runtime pause failed: unable to freeze: unknown
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#26427