github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2768] Ollama Not Running Failing to Load #1668

New Issue
Closed
opened 2026-04-12 11:38:23 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 11:38:23 -05:00
Owner
Copy Link

Originally created by @TankMan649 on GitHub (Feb 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2768

Originally assigned to: @dhiltgen on GitHub.

I keep encountering a problem with Ollama and when it has been solved I have no idea how it was solved and everything I am doing to solve it nothing works.
I am running a Python script with LangChain and Ollama testing it on a a simple Gradio interface. Let me emphasize this is a script that has worked before and NOTHING has changed in the code.

It is a very simple Q&A interface from a RAG pipeline with indexed documents located in a LanceDB.

I have an RTX 3060TI with 96GB RAM and 2xCPUs with 12 cores each for 24 total.

I needed show the Gradio test to someone today and when I run the Python script, Gradio fires up, the Python code code runs smoothly but when you type in a question everything just spins and spins forever. No error messages. No traceback. Nothing. It just doesn't come to an answer.

Now when it has worked before I see Ollama in the GPU process list using memory through nvidia-smi and in the process list using significant CPU core power through htop. Now however, I do not see Ollama in the GPU or CPU processes.

I have tried upgrading Ollama, downgrading, systemctl, restarting the system, I've updated the cuda (that was in a previous iteration of this problem and I thought that maybe played a role in helping solve it the first time...guess I was wrong). Absolutely no idea what the problem is.

Thoughts?

Originally created by @TankMan649 on GitHub (Feb 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2768 Originally assigned to: @dhiltgen on GitHub. I keep encountering a problem with Ollama and when it has been solved I have no idea how it was solved and everything I am doing to solve it nothing works. I am running a Python script with LangChain and Ollama testing it on a a simple Gradio interface. Let me emphasize this is a script that has worked before and NOTHING has changed in the code. It is a very simple Q&A interface from a RAG pipeline with indexed documents located in a LanceDB. I have an RTX 3060TI with 96GB RAM and 2xCPUs with 12 cores each for 24 total. I needed show the Gradio test to someone today and when I run the Python script, Gradio fires up, the Python code code runs smoothly but when you type in a question everything just spins and spins forever. No error messages. No traceback. Nothing. It just doesn't come to an answer. Now when it has worked before I see Ollama in the GPU process list using memory through nvidia-smi and in the process list using significant CPU core power through htop. Now however, I do not see Ollama in the GPU or CPU processes. I have tried upgrading Ollama, downgrading, systemctl, restarting the system, I've updated the cuda (that was in a previous iteration of this problem and I thought that maybe played a role in helping solve it the first time...guess I was wrong). Absolutely no idea what the problem is. Thoughts?
GiteaMirror commented 2026-04-12 11:38:25 -05:00
Author
Owner
Copy Link

@seanmavley commented on GitHub (Feb 26, 2024):

Any chance you can share you most recent logs?

It's likely not Ollama, but something on your system that's somehow someway changed

<!-- gh-comment-id:1965055982 --> @seanmavley commented on GitHub (Feb 26, 2024): Any chance you can share you most recent logs? It's likely not Ollama, but something on your system that's somehow someway changed
GiteaMirror commented 2026-04-12 11:38:26 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 11, 2024):

@TankMan649 without server logs it's hard to say what might be going wrong. If you're still having trouble, please upgrade to the latest release, and share your server log so we can see what it shows. It may be helpful to set OLLAMA_DEBUG=1 for the server to get more verbose logging.

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md

<!-- gh-comment-id:1989664554 --> @dhiltgen commented on GitHub (Mar 11, 2024): @TankMan649 without server logs it's hard to say what might be going wrong. If you're still having trouble, please upgrade to the latest release, and share your server log so we can see what it shows. It may be helpful to set `OLLAMA_DEBUG=1` for the server to get more verbose logging. https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md
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#1668
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?