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 #4720] Ollama unload model when embedding a large pdf file #2976

New Issue
Closed
opened 2026-04-12 13:21:26 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 13:21:26 -05:00
Owner
Copy Link

Originally created by @travisgu on GitHub (May 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4720

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Hi there,

I am using ollama to serve Qwen 72B model with a NVidia L20 card. And I am using AnythingLLM as the RAG tool. When doing embedding with small texts, it all works fine. But when with large amount of text, the model unloading itself after a few API calls. I enabled the debug log and here is the log:
image
The log shows the model was unloaded during embedding processing. Not sure why this happend. Please help, thanks!

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.38

Originally created by @travisgu on GitHub (May 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4720 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Hi there, I am using ollama to serve Qwen 72B model with a NVidia L20 card. And I am using AnythingLLM as the RAG tool. When doing embedding with small texts, it all works fine. But when with large amount of text, the model unloading itself after a few API calls. I enabled the debug log and here is the log: <img width="1689" alt="image" src="https://github.com/ollama/ollama/assets/10804665/ce891296-2392-4afe-b88c-fa95b49983e6"> The log shows the model was unloaded during embedding processing. Not sure why this happend. Please help, thanks! ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.38
GiteaMirror added the bug label 2026-04-12 13:21:26 -05:00
GiteaMirror commented 2026-04-12 13:21:27 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 30, 2024):

Hi there are you running this with OLLAMA_MAX_LOADED set to 2+?

<!-- gh-comment-id:2140091694 --> @jmorganca commented on GitHub (May 30, 2024): Hi there are you running this with `OLLAMA_MAX_LOADED` set to 2+?
GiteaMirror commented 2026-04-12 13:21:27 -05:00
Author
Owner
Copy Link

@travisgu commented on GitHub (May 31, 2024):

OLLAMA_MAX_LOADED_MODELS is 1
image

Hi there are you running this with OLLAMA_MAX_LOADED set to 2+?

<!-- gh-comment-id:2141106089 --> @travisgu commented on GitHub (May 31, 2024): OLLAMA_MAX_LOADED_MODELS is 1 <img width="1691" alt="image" src="https://github.com/ollama/ollama/assets/10804665/42816229-4f19-46c5-96d6-6be82b76bb68"> > Hi there are you running this with `OLLAMA_MAX_LOADED` set to 2+?
GiteaMirror commented 2026-04-12 13:21:28 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 26, 2024):

Please upgrade to the latest version, as concurrency has been enabled by default in 0.2.0 and up. You should see much better performance for RAG workflows using 2 models.

If you're still having trouble after upgrading, please share an updated server log (ideally the file/text, not a screen shot) and I'll reopen the issue.

<!-- gh-comment-id:2251604070 --> @dhiltgen commented on GitHub (Jul 26, 2024): Please upgrade to the latest version, as concurrency has been enabled by default in 0.2.0 and up. You should see much better performance for RAG workflows using 2 models. If you're still having trouble after upgrading, please share an updated server log (ideally the file/text, not a screen shot) and I'll reopen the issue.
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#2976
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?