github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3279] Mount model into pvc to get faster boot with init container #2021

New Issue
Closed
opened 2026-04-12 12:14:28 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:14:28 -05:00
Owner
Copy Link

Originally created by @didlawowo on GitHub (Mar 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3279

What are you trying to do?

when you're trying to use big model like 70b it take à lot of time to start with downloading. actually isn't possible to build ollama image with model inside

should be a good idea to create a bootstrap volume who download model into pvc

then when you. update your pod u don't have to download all model and just keep the pvc mounted in the previous pod

How should we solve this?

provide init container pvc loading model that describe model should be download and keep pvc persistent (with size / storageClass / etc

provide a bootstrap script to download local model from another llama url should be nice (ml engineer) can push their model into this pvc easily

What is the impact of not solving this?

very slow start and can't custom easily ollama with different model

Anything else?

should be happy to help you to do that.

Originally created by @didlawowo on GitHub (Mar 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3279 ### What are you trying to do? when you're trying to use big model like 70b it take à lot of time to start with downloading. actually isn't possible to build ollama image with model inside should be a good idea to create a bootstrap volume who download model into pvc then when you. update your pod u don't have to download all model and just keep the pvc mounted in the previous pod ### How should we solve this? provide init container pvc loading model that describe model should be download and keep pvc persistent (with size / storageClass / etc provide a bootstrap script to download local model from another llama url should be nice (ml engineer) can push their model into this pvc easily ### What is the impact of not solving this? very slow start and can't custom easily ollama with different model ### Anything else? should be happy to help you to do that.
GiteaMirror commented 2026-04-12 12:14:30 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Mar 22, 2024):

the kubernetes example is intended to be a very basic example of how to run ollama in a kubernetes deployment and should be consumed as exactly that, an example. it is not meant to be a full kubernetes solution

<!-- gh-comment-id:2015327828 --> @mxyng commented on GitHub (Mar 22, 2024): the kubernetes example is intended to be a very basic example of how to run ollama in a kubernetes deployment and should be consumed as exactly that, an example. it is not meant to be a full kubernetes solution
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2021
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?