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 #5477] How to setting N GPU usage? #65461

New Issue
Closed
opened 2026-05-03 21:22:18 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 21:22:18 -05:00
Owner
Copy Link

Originally created by @CaoYunzhou on GitHub (Jul 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5477

What is the issue?

why use one GPU
I have four gpu device
image

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.48

Originally created by @CaoYunzhou on GitHub (Jul 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5477 ### What is the issue? why use one GPU I have four gpu device ![image](https://github.com/ollama/ollama/assets/28099773/775bb006-e7de-48cf-b001-98a49ff66595) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.48
GiteaMirror added the bug label 2026-05-03 21:22:19 -05:00
GiteaMirror commented 2026-05-03 21:22:34 -05:00
Author
Owner
Copy Link

@CaoYunzhou commented on GitHub (Jul 4, 2024):

0   N/A  N/A     65952      C   ...unners/cuda_v11/ollama_llama_server      39122MiB
maybe only use number 0 deviced
<!-- gh-comment-id:2208195810 --> @CaoYunzhou commented on GitHub (Jul 4, 2024): 0 N/A N/A 65952 C ...unners/cuda_v11/ollama_llama_server 39122MiB maybe only use number 0 deviced
GiteaMirror commented 2026-05-03 21:22:36 -05:00
Author
Owner
Copy Link

@CaoYunzhou commented on GitHub (Jul 4, 2024):

I reslove find in issue
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
#Environment="CUDA_VISIBLE_DEVICES=32a47599-188e-dd99-4336-152ad66edb31,9e751506-fbbf-dc41-2475-60f78c4b87b8,db7c29cf-1f42-bbf7-04a4-c81b7eaa27b5,9bc1c429-31c1-8c38-7075-0de3e1992bd8"
#Environment="CUDA_VISIBLE_DEVICES=GPU-32a47599-188e-dd99-4336-152ad66edb31,GPU-9e751506-fbbf-dc41-2475-60f78c4b87b8,GPU-db7c29cf-1f42-bbf7-04a4-c81b7eaa27b5,GPU-9bc1c429-31c1-8c38-7075-0de3e1992bd8"
Environment="CUDA_VISIBLE_DEVICES=0,1,2,3"
Environment="OLLAMA_MAX_LOADED_MODELS=9"
Environment="OLLAMA_NUM_PARALLEL=100"
Environment="OLLAMA_HOST=0.0.0.0:11434"

User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"

[Install]
WantedBy=default.target

#-----------
need this env is working
Environment="CUDA_VISIBLE_DEVICES=0,1,2,3"
Environment="OLLAMA_MAX_LOADED_MODELS=9"
Environment="OLLAMA_NUM_PARALLEL=100"
Environment="OLLAMA_HOST=0.0.0.0:11434"

<!-- gh-comment-id:2208291659 --> @CaoYunzhou commented on GitHub (Jul 4, 2024): I reslove find in issue [Unit] Description=Ollama Service After=network-online.target [Service] ExecStart=/usr/local/bin/ollama serve #Environment="CUDA_VISIBLE_DEVICES=32a47599-188e-dd99-4336-152ad66edb31,9e751506-fbbf-dc41-2475-60f78c4b87b8,db7c29cf-1f42-bbf7-04a4-c81b7eaa27b5,9bc1c429-31c1-8c38-7075-0de3e1992bd8" #Environment="CUDA_VISIBLE_DEVICES=GPU-32a47599-188e-dd99-4336-152ad66edb31,GPU-9e751506-fbbf-dc41-2475-60f78c4b87b8,GPU-db7c29cf-1f42-bbf7-04a4-c81b7eaa27b5,GPU-9bc1c429-31c1-8c38-7075-0de3e1992bd8" Environment="CUDA_VISIBLE_DEVICES=0,1,2,3" Environment="OLLAMA_MAX_LOADED_MODELS=9" Environment="OLLAMA_NUM_PARALLEL=100" Environment="OLLAMA_HOST=0.0.0.0:11434" User=ollama Group=ollama Restart=always RestartSec=3 Environment="PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin" [Install] WantedBy=default.target #----------- need this env is working Environment="CUDA_VISIBLE_DEVICES=0,1,2,3" Environment="OLLAMA_MAX_LOADED_MODELS=9" Environment="OLLAMA_NUM_PARALLEL=100" Environment="OLLAMA_HOST=0.0.0.0:11434"
GiteaMirror commented 2026-05-03 21:22:38 -05:00
Author
Owner
Copy Link

@haier-1314 commented on GitHub (Jul 15, 2024):

I have the same problem, please tell me how to solve it

<!-- gh-comment-id:2227597649 --> @haier-1314 commented on GitHub (Jul 15, 2024): I have the same problem, please tell me how to solve it
GiteaMirror commented 2026-05-03 21:22:40 -05:00
Author
Owner
Copy Link

@CaoYunzhou commented on GitHub (Jul 16, 2024):

need this env is working
Environment="CUDA_VISIBLE_DEVICES=0,1,2,3"
Environment="OLLAMA_MAX_LOADED_MODELS=9"
Environment="OLLAMA_NUM_PARALLEL=100"
Environment="OLLAMA_HOST=0.0.0.0:11434"

in your system setting change this ollama env service
need this env is working
Environment="CUDA_VISIBLE_DEVICES=0,1,2,3"
Environment="OLLAMA_MAX_LOADED_MODELS=9"
Environment="OLLAMA_NUM_PARALLEL=100"
Environment="OLLAMA_HOST=0.0.0.0:11434"

<!-- gh-comment-id:2230584577 --> @CaoYunzhou commented on GitHub (Jul 16, 2024): > need this env is working > Environment="CUDA_VISIBLE_DEVICES=0,1,2,3" > Environment="OLLAMA_MAX_LOADED_MODELS=9" > Environment="OLLAMA_NUM_PARALLEL=100" > Environment="OLLAMA_HOST=0.0.0.0:11434" in your system setting change this ollama env service need this env is working Environment="CUDA_VISIBLE_DEVICES=0,1,2,3" Environment="OLLAMA_MAX_LOADED_MODELS=9" Environment="OLLAMA_NUM_PARALLEL=100" Environment="OLLAMA_HOST=0.0.0.0:11434"
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#65461
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?