github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6510] Performing GET request to registry.ollama.ai/v2/ returns 404 page not found #50609

New Issue
Open
opened 2026-04-28 16:31:44 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 16:31:44 -05:00
Owner
Copy Link

Originally created by @yeahdongcn on GitHub (Aug 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6510

What is the issue?

Background:

Kubernetes 1.31 introduced a new feature: Read-Only Volumes Based on OCI Artifacts. I believe this feature could be very useful for deploying a dedicated model alongside Ollama in Kubernetes.

The currently supported container runtime is CRI-O, which relies on containers/image for all image-related operations. It uses a GET request to the following URL to determine the appropriate schema: e.g. https://registry.ollama.ai/v2/.

I hardcoded the schema to HTTPS and used the Ollama image registry.ollama.ai/library/tinyllama:latest as the OCI image volume. After making some modifications to the modules consumed by CRI-O, I was able to get the pod and container running without any issues.

Please see the following logs:

❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock run ./container.json ./sandbox_config.json
INFO[0005] Pulling container image: registry.docker.com/ollama/ollama:latest 
INFO[0005] Pulling image registry.ollama.ai/library/tinyllama:latest to be mounted to container path: /volume 
7e437894449f6429799cc5ef236c4a4570a69e3769bf324bbf700045e383cae8
❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock ps
CONTAINER           IMAGE                                        CREATED             STATE               NAME                ATTEMPT             POD ID              POD
7e437894449f6       registry.docker.com/ollama/ollama:latest     8 seconds ago       Running             podsandbox-sleep    0                   4d1766fdf286b       unknown
❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock exec -it 7e437894449f6 bash
root@crictl_host:/# cd volume/
root@crictl_host:/volume# ls -l
total 622772
-rw-r--r-- 1 root root 637699456 Aug 26 08:32 model
-rw-r--r-- 1 root root        98 Aug 26 08:32 params
-rw-r--r-- 1 root root        31 Aug 26 08:32 system
-rw-r--r-- 1 root root        70 Aug 26 08:32 template
root@crictl_host:/volume#

I'm wondering if the Ollama model registry could be slightly updated to handle requests to registry.ollama.ai/v2/. This would allow certain container runtimes to seamlessly integrate Ollama's OCI models without any issues.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.6

Originally created by @yeahdongcn on GitHub (Aug 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6510 ### What is the issue? Background: Kubernetes 1.31 introduced a new feature: [Read-Only Volumes Based on OCI Artifacts](https://kubernetes.io/blog/2024/08/16/kubernetes-1-31-image-volume-source/). I believe this feature could be very useful for deploying a dedicated model alongside Ollama in Kubernetes. The currently supported container runtime is [CRI-O](https://github.com/cri-o/cri-o), which relies on [containers/image](https://github.com/containers/image) for all image-related operations. It uses a `GET` request to the following URL to [determine](https://github.com/containers/image/blob/main/docker/docker_client.go#L903) the appropriate schema: e.g. https://registry.ollama.ai/v2/. I hardcoded the schema to `HTTPS` and used the Ollama image `registry.ollama.ai/library/tinyllama:latest` as the OCI image volume. After making some modifications to the modules consumed by CRI-O, I was able to get the pod and container running without any issues. Please see the following logs: ```bash ❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock run ./container.json ./sandbox_config.json INFO[0005] Pulling container image: registry.docker.com/ollama/ollama:latest INFO[0005] Pulling image registry.ollama.ai/library/tinyllama:latest to be mounted to container path: /volume 7e437894449f6429799cc5ef236c4a4570a69e3769bf324bbf700045e383cae8 ❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock ps CONTAINER IMAGE CREATED STATE NAME ATTEMPT POD ID POD 7e437894449f6 registry.docker.com/ollama/ollama:latest 8 seconds ago Running podsandbox-sleep 0 4d1766fdf286b unknown ❯ sudo crictl --timeout=200s --runtime-endpoint unix:///run/crio/crio.sock exec -it 7e437894449f6 bash root@crictl_host:/# cd volume/ root@crictl_host:/volume# ls -l total 622772 -rw-r--r-- 1 root root 637699456 Aug 26 08:32 model -rw-r--r-- 1 root root 98 Aug 26 08:32 params -rw-r--r-- 1 root root 31 Aug 26 08:32 system -rw-r--r-- 1 root root 70 Aug 26 08:32 template root@crictl_host:/volume# ``` I'm wondering if the Ollama model registry could be slightly updated to handle requests to `registry.ollama.ai/v2/`. This would allow certain container runtimes to seamlessly integrate Ollama's OCI models without any issues. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.6
GiteaMirror added the bug label 2026-04-28 16:31:44 -05:00
GiteaMirror commented 2026-04-28 16:31:51 -05:00
Author
Owner
Copy Link

@yeahdongcn commented on GitHub (Aug 26, 2024):

BTW, I also tried pushing the image to Harbor and Nexus, and they both handle the %s://%s/v2/ URL correctly.

<!-- gh-comment-id:2309691677 --> @yeahdongcn commented on GitHub (Aug 26, 2024): BTW, I also tried pushing the image to Harbor and Nexus, and they both handle the `%s://%s/v2/` URL correctly.
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 bug
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#50609
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?