github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9145] Manual install, and Adding Ollama as a startup service (recommended) but Error: could not connect to ollama app, is it running? #5950

New Issue
Closed
opened 2026-04-12 17:17:44 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 17:17:44 -05:00
Owner
Copy Link

Originally created by @ye7love7 on GitHub (Feb 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9145

显卡“：单卡3090 24G，内存：250G
按照https://github.com/ollama/ollama/blob/main/docs/linux.md执行了安装，并且添加了startup service：

sudo nano /etc/systemd/system/ollama.service
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
# 设置 GPU 加载层数
# Environment="OLLAMA_GPU_LAYERS=10"
# 设置 keep-alive 时间为 10 分钟
Environment="OLLAMA_KEEP_ALIVE=10m"
# 设置 host 和 port
Environment="OLLAMA_HOST=0.0.0.0:8080"
# 设置模型路径
Environment="OLLAMA_MODELS=/home/tskj/MOD/ollama_models"
Environment="PATH=$PATH"
Environment="OLLAMA_DEBUG=1"
ExecStart=/usr/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
[Install]
WantedBy=default.target

sudo systemctl status ollama显示如下：

● ollama.service - Ollama Service
     Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled)
     Active: active (running) since Sat 2025-02-15 23:56:25 CST; 9h ago
   Main PID: 1403868 (ollama)
      Tasks: 22 (limit: 309002)
     Memory: 17.5M
        CPU: 2.754s
     CGroup: /system.slice/ollama.service
             └─1403868 /usr/bin/ollama serve

Feb 15 23:56:26 tskj ollama[1403868]: CUDA driver version: 12.4
Feb 15 23:56:26 tskj ollama[1403868]: calling cuDeviceGetCount
Feb 15 23:56:26 tskj ollama[1403868]: device count 1
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.090+08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux->
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA totalMem 24252 mb
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA freeMem 21542 mb
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] Compute Capability 8.6
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu"
Feb 15 23:56:26 tskj ollama[1403868]: releasing cuda driver library
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-866b9226-469d-27c8-6ae4-99>

看样子识别到了显卡。

(base) tskj@tskj:~$ journalctl -u ollama -e
Feb 15 23:56:26 tskj ollama[1403868]: 2025/02/15 23:56:26 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVIC>
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=images.go:432 msg="total blobs: 0"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:8080 (version 0.5.11)"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA"
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=libcuda.so*
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[/usr/lib/ollama/libcuda.s>
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.064+08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[/usr/lib/x86_64-lin>
Feb 15 23:56:26 tskj ollama[1403868]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.120
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuInit - 0x7f95e96aebc0
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDriverGetVersion - 0x7f95e96aebe0
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetCount - 0x7f95e96aec20
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGet - 0x7f95e96aec00
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetAttribute - 0x7f95e96aed00
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetUuid - 0x7f95e96aec60
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetName - 0x7f95e96aec40
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuCtxCreate_v3 - 0x7f95e96aeee0
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuMemGetInfo_v2 - 0x7f95e96b8e20
Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuCtxDestroy - 0x7f95e9713850
Feb 15 23:56:26 tskj ollama[1403868]: calling cuInit
Feb 15 23:56:26 tskj ollama[1403868]: calling cuDriverGetVersion
Feb 15 23:56:26 tskj ollama[1403868]: raw version 0x2f08
Feb 15 23:56:26 tskj ollama[1403868]: CUDA driver version: 12.4
Feb 15 23:56:26 tskj ollama[1403868]: calling cuDeviceGetCount
Feb 15 23:56:26 tskj ollama[1403868]: device count 1
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.090+08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux->
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA totalMem 24252 mb
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA freeMem 21542 mb
Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] Compute Capability 8.6
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu"
Feb 15 23:56:26 tskj ollama[1403868]: releasing cuda driver library
Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-866b9226-469d-27c8-6ae4-99>
lines 967-1000/1000 (END)

似乎端口也监听到了8080，好像一切都正常启动了，但是ollama list:Error: could not connect to ollama app, is it running?
已经尝试卸载、重装，但是依然是这个问题，求大哥们解决！

Originally created by @ye7love7 on GitHub (Feb 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9145 显卡“：单卡3090 24G，内存：250G 按照https://github.com/ollama/ollama/blob/main/docs/linux.md执行了安装，并且添加了startup service： ``` sudo nano /etc/systemd/system/ollama.service [Unit] Description=Ollama Service After=network-online.target [Service] # 设置 GPU 加载层数 # Environment="OLLAMA_GPU_LAYERS=10" # 设置 keep-alive 时间为 10 分钟 Environment="OLLAMA_KEEP_ALIVE=10m" # 设置 host 和 port Environment="OLLAMA_HOST=0.0.0.0:8080" # 设置模型路径 Environment="OLLAMA_MODELS=/home/tskj/MOD/ollama_models" Environment="PATH=$PATH" Environment="OLLAMA_DEBUG=1" ExecStart=/usr/bin/ollama serve User=ollama Group=ollama Restart=always RestartSec=3 [Install] WantedBy=default.target ``` sudo systemctl status ollama显示如下： ``` ● ollama.service - Ollama Service Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled) Active: active (running) since Sat 2025-02-15 23:56:25 CST; 9h ago Main PID: 1403868 (ollama) Tasks: 22 (limit: 309002) Memory: 17.5M CPU: 2.754s CGroup: /system.slice/ollama.service └─1403868 /usr/bin/ollama serve Feb 15 23:56:26 tskj ollama[1403868]: CUDA driver version: 12.4 Feb 15 23:56:26 tskj ollama[1403868]: calling cuDeviceGetCount Feb 15 23:56:26 tskj ollama[1403868]: device count 1 Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.090+08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux-> Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA totalMem 24252 mb Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA freeMem 21542 mb Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] Compute Capability 8.6 Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu" Feb 15 23:56:26 tskj ollama[1403868]: releasing cuda driver library Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-866b9226-469d-27c8-6ae4-99> ``` 看样子识别到了显卡。 ``` (base) tskj@tskj:~$ journalctl -u ollama -e Feb 15 23:56:26 tskj ollama[1403868]: 2025/02/15 23:56:26 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVIC> Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=images.go:432 msg="total blobs: 0" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:8080 (version 0.5.11)" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.032+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA" Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=libcuda.so* Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.059+08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[/usr/lib/ollama/libcuda.s> Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.064+08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[/usr/lib/x86_64-lin> Feb 15 23:56:26 tskj ollama[1403868]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.120 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuInit - 0x7f95e96aebc0 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDriverGetVersion - 0x7f95e96aebe0 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetCount - 0x7f95e96aec20 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGet - 0x7f95e96aec00 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetAttribute - 0x7f95e96aed00 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetUuid - 0x7f95e96aec60 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuDeviceGetName - 0x7f95e96aec40 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuCtxCreate_v3 - 0x7f95e96aeee0 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuMemGetInfo_v2 - 0x7f95e96b8e20 Feb 15 23:56:26 tskj ollama[1403868]: dlsym: cuCtxDestroy - 0x7f95e9713850 Feb 15 23:56:26 tskj ollama[1403868]: calling cuInit Feb 15 23:56:26 tskj ollama[1403868]: calling cuDriverGetVersion Feb 15 23:56:26 tskj ollama[1403868]: raw version 0x2f08 Feb 15 23:56:26 tskj ollama[1403868]: CUDA driver version: 12.4 Feb 15 23:56:26 tskj ollama[1403868]: calling cuDeviceGetCount Feb 15 23:56:26 tskj ollama[1403868]: device count 1 Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.090+08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux-> Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA totalMem 24252 mb Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] CUDA freeMem 21542 mb Feb 15 23:56:26 tskj ollama[1403868]: [GPU-866b9226-469d-27c8-6ae4-99b9d17d5cf6] Compute Capability 8.6 Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu" Feb 15 23:56:26 tskj ollama[1403868]: releasing cuda driver library Feb 15 23:56:26 tskj ollama[1403868]: time=2025-02-15T23:56:26.306+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-866b9226-469d-27c8-6ae4-99> lines 967-1000/1000 (END) ``` 似乎端口也监听到了8080，好像一切都正常启动了，但是ollama list:Error: could not connect to ollama app, is it running? 已经尝试卸载、重装，但是依然是这个问题，求大哥们解决！
GiteaMirror commented 2026-04-12 17:17:46 -05:00
Author
Owner
Copy Link

@ye7love7 commented on GitHub (Feb 16, 2025):

我设置Environment="OLLAMA_HOST=0.0.0.0，监听到11434，ollama list就可以正常启动，这是什么原因？

<!-- gh-comment-id:2661181874 --> @ye7love7 commented on GitHub (Feb 16, 2025): 我设置Environment="OLLAMA_HOST=0.0.0.0，监听到11434，ollama list就可以正常启动，这是什么原因？
GiteaMirror commented 2026-04-12 17:17:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 16, 2025):

You have to set OLLAMA_HOST=0.0.0.0:8080 in the client environment as well as the server environment.

OLLAMA_HOST=0.0.0.0:8080 ollama list
<!-- gh-comment-id:2661376164 --> @rick-github commented on GitHub (Feb 16, 2025): You have to set `OLLAMA_HOST=0.0.0.0:8080` in the client environment as well as the server environment. ``` OLLAMA_HOST=0.0.0.0:8080 ollama list ```
GiteaMirror commented 2026-04-12 17:17:47 -05:00
Author
Owner
Copy Link

@ye7love7 commented on GitHub (Feb 19, 2025):

You have to set OLLAMA_HOST=0.0.0.0:8080 in the client environment as well as the server environment.

OLLAMA_HOST=0.0.0.0:8080 ollama list

right,thanks a lot!

<!-- gh-comment-id:2667277786 --> @ye7love7 commented on GitHub (Feb 19, 2025): > You have to set `OLLAMA_HOST=0.0.0.0:8080` in the client environment as well as the server environment. > > ``` > OLLAMA_HOST=0.0.0.0:8080 ollama list > ``` right,thanks a lot!
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#5950
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?