github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5114] Ollama not loading in gpu with docker on latest version but works on 0.1.31 which doesn't have multi-user concurrency #3227

New Issue
Closed
opened 2026-04-12 13:44:03 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 13:44:03 -05:00
Owner
Copy Link

Originally created by @bluenevus on GitHub (Jun 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5114

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Absolutely excited to see you have multi-user concurrency. I setup ollama on docker with 8 gpus. I could get 2 models to run in gpu each with their own container, Llava and Llamaguard2. No other models would load into gpu even if there are no other gpus using it. I tried --gpus= 2, I tried --gpus '"device=0,1"' and I tried device all, no luck only those 2 specific models loaded and I could only get it to load if I assigned only 1 device like so --gpus device=1. I read through the issues and there was one comment to go back to 0.1.31 but it seems no multi-user concurrency on that with this -e OLLAMA_NUM_PARALLEL=10. I tried this on 4090, rtx8ks, A6000s and they all have the same issue with v0.1.44

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

v0.1.44

Originally created by @bluenevus on GitHub (Jun 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5114 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Absolutely excited to see you have multi-user concurrency. I setup ollama on docker with 8 gpus. I could get 2 models to run in gpu each with their own container, Llava and Llamaguard2. No other models would load into gpu even if there are no other gpus using it. I tried --gpus= 2, I tried --gpus '"device=0,1"' and I tried device all, no luck only those 2 specific models loaded and I could only get it to load if I assigned only 1 device like so --gpus device=1. I read through the issues and there was one comment to go back to 0.1.31 but it seems no multi-user concurrency on that with this -e OLLAMA_NUM_PARALLEL=10. I tried this on 4090, rtx8ks, A6000s and they all have the same issue with v0.1.44 ### OS Linux, Docker ### GPU Nvidia ### CPU Intel ### Ollama version v0.1.44
GiteaMirror added the bug label 2026-04-12 13:44:03 -05:00
GiteaMirror commented 2026-04-12 13:44:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

To clarify, OLLAMA_NUM_PARALLEL only allows multiple concurrent requests to a given model. To load multiple models, you need to adjust OLLAMA_MAX_LOADED_MODELS, which is what it sounds like you're trying to do. Be aware high parallel settings will lead to a lot of VRAM usage as it has to multiply the context size to handle the concurrent requests. You'll see the results of this via ollama ps and the VRAM usage.

(hint: you can now run ollama serve --help to get a quick synopsis on the settings that are available)

<!-- gh-comment-id:2176603398 --> @dhiltgen commented on GitHub (Jun 18, 2024): To clarify, OLLAMA_NUM_PARALLEL only allows multiple concurrent requests to a given model. To load multiple models, you need to adjust OLLAMA_MAX_LOADED_MODELS, which is what it sounds like you're trying to do. Be aware high parallel settings will lead to a lot of VRAM usage as it has to multiply the context size to handle the concurrent requests. You'll see the results of this via `ollama ps` and the VRAM usage. (hint: you can now run `ollama serve --help` to get a quick synopsis on the settings that are available)
GiteaMirror commented 2026-04-12 13:44:07 -05:00
Author
Owner
Copy Link

@bluenevus commented on GitHub (Jun 18, 2024):

Thanks. Yes, I'm only trying to do multiple concurrent connection and that doesn't work. I'm not trying to load multiple models from the same container. I have one container per model per gpu or gpus attached.

<!-- gh-comment-id:2176631611 --> @bluenevus commented on GitHub (Jun 18, 2024): Thanks. Yes, I'm only trying to do multiple concurrent connection and that doesn't work. I'm not trying to load multiple models from the same container. I have one container per model per gpu or gpus attached.
GiteaMirror commented 2026-04-12 13:44:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 19, 2024):

Can you share the server logs, so I can try to understand why it isn't setting up for parallel requests?

<!-- gh-comment-id:2177306225 --> @dhiltgen commented on GitHub (Jun 19, 2024): Can you share the server logs, so I can try to understand why it isn't setting up for parallel requests?
GiteaMirror commented 2026-04-12 13:44:11 -05:00
Author
Owner
Copy Link

@bluenevus commented on GitHub (Jun 19, 2024):

Thanks, I just removed ollama everywhere and went with vllm. I appreciate your fast response and help though and wish ollama the best. Its an amazing product with an amazing team doing great work.

<!-- gh-comment-id:2177312587 --> @bluenevus commented on GitHub (Jun 19, 2024): Thanks, I just removed ollama everywhere and went with vllm. I appreciate your fast response and help though and wish ollama the best. Its an amazing product with an amazing team doing great work.
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#3227
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?