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 #3275] Resumable ollama push #2018

New Issue
Open
opened 2026-04-12 12:14:19 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 12:14:19 -05:00
Owner
Copy Link

Originally created by @sammcj on GitHub (Mar 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3275

What is the issue?

When pushing models to ollama.com's registry, if they fail part way through - when you go to continue the push they start from scratch again.

This is quite painful when you've spent hours trying to upload from Australian a slow internet link as it can mean many hours of uploading and hoping for the best.

SCR-20240321-gzoz SCR-20240321-gzvk

What did you expect to see?

Errors happen, things fail - but they should be resumable (at least for say 24hrs).

I expected to run the push and have it pickup where it left off (around 8%).

Steps to reproduce

  • Come to Australia, enjoy our fine internet infrastructure.
  • Push a large model to ollama.com
  • Take pleasure in the chance game which is Australian internet reliability.
  • When your upload fails, try to continue the upload by pushing again.
  • Tears.

Are there any recent changes that introduced the issue?

No response

OS

Linux, macOS

Architecture

arm64, amd64

Platform

No response

Ollama version

0.1.29

GPU

Nvidia, Apple

GPU info

N/A

CPU

AMD, Apple

Other software

No response

Originally created by @sammcj on GitHub (Mar 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3275 ### What is the issue? When pushing models to ollama.com's registry, if they fail part way through - when you go to continue the push they start from scratch again. This is quite painful when you've spent hours trying to upload from ~~Australian~~ a slow internet link as it can mean many hours of uploading and hoping for the best. <img width="1678" alt="SCR-20240321-gzoz" src="https://github.com/ollama/ollama/assets/862951/f3dec809-4445-428e-8b70-3d4f7b9eb1da"> <img width="1675" alt="SCR-20240321-gzvk" src="https://github.com/ollama/ollama/assets/862951/d8d1e4ee-358d-4dd8-815c-c5b9bfc24dd6"> ### What did you expect to see? Errors happen, things fail - but they should be resumable (at least for say 24hrs). I expected to run the push and have it pickup where it left off (around 8%). ### Steps to reproduce - Come to Australia, enjoy our fine internet infrastructure. - Push a large model to ollama.com - Take pleasure in the chance game which is Australian internet reliability. - When your upload fails, try to continue the upload by pushing again. - Tears. ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux, macOS ### Architecture arm64, amd64 ### Platform _No response_ ### Ollama version 0.1.29 ### GPU Nvidia, Apple ### GPU info N/A ### CPU AMD, Apple ### Other software _No response_
GiteaMirror added the networkingfeature request labels 2026-04-12 12:14:19 -05:00
GiteaMirror commented 2026-04-12 12:14:20 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 25, 2024):

Hi @sammcj, sorry about this. Resuming on push is on our radar.

<!-- gh-comment-id:2018528704 --> @BruceMacD commented on GitHub (Mar 25, 2024): Hi @sammcj, sorry about this. Resuming on push is on our radar.
GiteaMirror commented 2026-04-12 12:14:22 -05:00
Author
Owner
Copy Link

@bmizerany commented on GitHub (Mar 4, 2025):

We're still working on something tell help here. Stay tuned.

<!-- gh-comment-id:2696455468 --> @bmizerany commented on GitHub (Mar 4, 2025): We're still working on something tell help here. Stay tuned.
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 feature request networking
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#2018
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?