github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6369] Ubuntu22.04 - Warning: could not connect to a running Ollama instance #29760

New Issue
Closed
opened 2026-04-22 08:57:39 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 08:57:39 -05:00
Owner
Copy Link

Originally created by @ACodingfreak on GitHub (Aug 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6369

What is the issue?

I am not able to access ollama instance as shown in below logs, eventhough I am able to access the same before.

$ ollama --version 
Warning: could not connect to a running Ollama instance
Warning: client version is 0.3.4

$  systemctl status ollama
● ollama.service - Ollama Service
     Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled)
    Drop-In: /etc/systemd/system/ollama.service.d
             └─override.conf
     Active: active (running) since Wed 2024-08-14 19:56:09 PDT; 35min ago
   Main PID: 772316 (ollama)
      Tasks: 17 (limit: 76755)
     Memory: 1.1G
        CPU: 6.959s
     CGroup: /system.slice/ollama.service
             └─772316 /usr/local/bin/ollama serve

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

[Service]
Environment="OLLAMA_HOST=10.10.26.188"
Environment="OLLAMA_MODELS=/opt/ollama/models/"
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/cuda-12.3/bin:/usr/local/cuda-12.3/bin:/usr/local/cuda-12.3/bin:/home/codingfreak/anaconda3/envs/llama3_test/bin:/home/codingfreak/anaconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"

[Install]
WantedBy=default.target

Then I upgraded the same as shown below


$ curl -fsSL https://ollama.com/install.sh | sh
>>> Downloading ollama...
######################################################################## 100.0%##O#-#                                               ######################################################################## 100.0%
>>> Installing ollama to /usr/local/bin...
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
>>> NVIDIA GPU installed.
$ sudo systemctl daemon-reload
$ sudo systemctl enable ollama

$ ollama --version 
Warning: could not connect to a running Ollama instance
Warning: client version is 0.3.6

$ sudo systemctl status ollama
● ollama.service - Ollama Service
     Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled)
    Drop-In: /etc/systemd/system/ollama.service.d
             └─override.conf
     Active: active (running) since Wed 2024-08-14 20:39:16 PDT; 6min ago
   Main PID: 785243 (ollama)
      Tasks: 16 (limit: 76755)
     Memory: 1.1G
        CPU: 6.766s
     CGroup: /system.slice/ollama.service
             └─785243 /usr/local/bin/ollama serve

Aug 14 20:39:16 gpu01 systemd[1]: Started Ollama Service.
Aug 14 20:39:16 gpu01 ollama[785243]: 2024/08/14 20:39:16 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEV>
Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.849-07:00 level=INFO source=images.go:782 msg="total blobs: 0"
Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=images.go:790 msg="total unused blobs re>
Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=routes.go:1172 msg="Listening on 10.10.2>
Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=payload.go:30 msg="extracting embedded f>
Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.216-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries>
Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.216-07:00 level=INFO source=gpu.go:204 msg="looking for compatible G>
Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.298-07:00 level=INFO source=types.go:105 msg="inference compute" id=>

Loga

Aug 14 21:02:33 gpu01 systemd[1]: ollama.service: Consumed 6.913s CPU time.                                                [62/8875]
Aug 14 21:02:33 gpu01 systemd[1]: Started Ollama Service.                                                                           
Aug 14 21:02:33 gpu01 ollama[808132]: 2024/08/14 21:02:33 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVI
CE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://10.10.2
6.188:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA
_MODELS:/opt/ollama/models/ OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https
://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http:/
/0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:fals
e OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"                                                                                            
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.695-07:00 level=INFO source=images.go:782 msg="total blobs: 0"       
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.696-07:00 level=INFO source=images.go:790 msg="total unused blobs rem
oved: 0"                                                                                                                            
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.696-07:00 level=INFO source=routes.go:1172 msg="Listening on 10.10.26
.188:11434 (version 0.3.6)"                                                                                                         
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=INFO source=payload.go:30 msg="extracting embedded fi
les" dir=/tmp/ollama120779224/runners                                                                                               
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp
u file=build/linux/x86_64/cpu/bin/ollama_llama_server.gz                                                                            
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp
u_avx file=build/linux/x86_64/cpu_avx/bin/ollama_llama_server.gz
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp
u_avx2 file=build/linux/x86_64/cpu_avx2/bin/ollama_llama_server.gz 
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu
da_v11 file=build/linux/x86_64/cuda_v11/bin/libcublas.so.11.gz
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu
da_v11 file=build/linux/x86_64/cuda_v11/bin/libcublasLt.so.11.gz
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu
da_v11 file=build/linux/x86_64/cuda_v11/bin/libcudart.so.11.0.gz
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu
da_v11 file=build/linux/x86_64/cuda_v11/bin/ollama_llama_server.gz 
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=ro
cm_v60102 file=build/linux/x86_64/rocm_v60102/bin/deps.txt.gz
Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=ro
cm_v60102 file=build/linux/x86_64/rocm_v60102/bin/ollama_llama_server.gz
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo
und" file=/tmp/ollama120779224/runners/cpu/ollama_llama_server
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo
und" file=/tmp/ollama120779224/runners/cpu_avx/ollama_llama_server 
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo
und" file=/tmp/ollama120779224/runners/cpu_avx2/ollama_llama_server                                                                 
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo
und" file=/tmp/ollama120779224/runners/cuda_v11/ollama_llama_server
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo
und" file=/tmp/ollama120779224/runners/rocm_v60102/ollama_llama_server
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries 
[cuda_v11 rocm_v60102 cpu cpu_avx cpu_avx2]"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:45 msg="Override detection lo
gic by setting OLLAMA_LLM_LIBRARY"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler
"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=INFO source=gpu.go:204 msg="looking for compatible GP
Us"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:90 msg="searching for GPU discove
ry libraries for NVIDIA"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:472 msg="Searching for GPU librar
y" name=libcuda.so*
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:491 msg="gpu library search" glob
s="[/libcuda.so** /usr/local/cuda*/targets/*/lib/libcuda.so* /usr/lib/*-linux-gnu/nvidia/current/libcuda.so* /usr/lib/*-linux-gnu/li
bcuda.so* /usr/lib/wsl/lib/libcuda.so* /usr/lib/wsl/drivers/*/libcuda.so* /opt/cuda/lib*/libcuda.so* /usr/local/cuda/lib*/libcuda.so
* /usr/lib*/libcuda.so* /usr/local/lib*/libcuda.so*]"
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.046-07:00 level=DEBUG source=gpu.go:525 msg="discovered GPU libraries
" paths="[/usr/lib/i386-linux-gnu/libcuda.so.535.183.01 /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01]"
Aug 14 21:02:36 gpu01 ollama[808132]: library /usr/lib/i386-linux-gnu/libcuda.so.535.183.01 load err: /usr/lib/i386-linux-gnu/libcud
a.so.535.183.01: wrong ELF class: ELFCLASS32
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.047-07:00 level=DEBUG source=gpu.go:566 msg="skipping 32bit library" 
library=/usr/lib/i386-linux-gnu/libcuda.so.535.183.01
Aug 14 21:02:36 gpu01 ollama[808132]: CUDA driver version: 12.2
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.061-07:00 level=DEBUG source=gpu.go:123 msg="detected GPUs" count=1 l
ibrary=/usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01
Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] CUDA totalMem 12044 mb
Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] CUDA freeMem 11919 mb
Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] Compute Capability 8.6
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.129-07:00 level=DEBUG source=amd_linux.go:371 msg="amdgpu driver not 
detected /sys/module/amdgpu"
Aug 14 21:02:36 gpu01 ollama[808132]: releasing cuda driver library
Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.129-07:00 level=INFO source=types.go:105 msg="inference compute" id=G
PU-838e39e8-08a3-37c0-85d9-66182a7927ba library=cuda compute=8.6 driver=12.2 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" availab
le="11.6 GiB"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.4

Originally created by @ACodingfreak on GitHub (Aug 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6369 ### What is the issue? I am not able to access ollama instance as shown in below logs, eventhough I am able to access the same before. ``` $ ollama --version Warning: could not connect to a running Ollama instance Warning: client version is 0.3.4 $ systemctl status ollama ● ollama.service - Ollama Service Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled) Drop-In: /etc/systemd/system/ollama.service.d └─override.conf Active: active (running) since Wed 2024-08-14 19:56:09 PDT; 35min ago Main PID: 772316 (ollama) Tasks: 17 (limit: 76755) Memory: 1.1G CPU: 6.959s CGroup: /system.slice/ollama.service └─772316 /usr/local/bin/ollama serve $ cat /etc/systemd/system/ollama.service [Unit] Description=Ollama Service After=network-online.target [Service] Environment="OLLAMA_HOST=10.10.26.188" Environment="OLLAMA_MODELS=/opt/ollama/models/" ExecStart=/usr/local/bin/ollama serve User=ollama Group=ollama Restart=always RestartSec=3 Environment="PATH=/usr/local/cuda-12.3/bin:/usr/local/cuda-12.3/bin:/usr/local/cuda-12.3/bin:/home/codingfreak/anaconda3/envs/llama3_test/bin:/home/codingfreak/anaconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin" [Install] WantedBy=default.target ``` Then I upgraded the same as shown below ``` $ curl -fsSL https://ollama.com/install.sh | sh >>> Downloading ollama... ######################################################################## 100.0%##O#-# ######################################################################## 100.0% >>> Installing ollama to /usr/local/bin... >>> Adding ollama user to render group... >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> Enabling and starting ollama service... >>> NVIDIA GPU installed. $ sudo systemctl daemon-reload $ sudo systemctl enable ollama $ ollama --version Warning: could not connect to a running Ollama instance Warning: client version is 0.3.6 $ sudo systemctl status ollama ● ollama.service - Ollama Service Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled) Drop-In: /etc/systemd/system/ollama.service.d └─override.conf Active: active (running) since Wed 2024-08-14 20:39:16 PDT; 6min ago Main PID: 785243 (ollama) Tasks: 16 (limit: 76755) Memory: 1.1G CPU: 6.766s CGroup: /system.slice/ollama.service └─785243 /usr/local/bin/ollama serve Aug 14 20:39:16 gpu01 systemd[1]: Started Ollama Service. Aug 14 20:39:16 gpu01 ollama[785243]: 2024/08/14 20:39:16 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEV> Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.849-07:00 level=INFO source=images.go:782 msg="total blobs: 0" Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=images.go:790 msg="total unused blobs re> Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=routes.go:1172 msg="Listening on 10.10.2> Aug 14 20:39:16 gpu01 ollama[785243]: time=2024-08-14T20:39:16.850-07:00 level=INFO source=payload.go:30 msg="extracting embedded f> Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.216-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries> Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.216-07:00 level=INFO source=gpu.go:204 msg="looking for compatible G> Aug 14 20:39:19 gpu01 ollama[785243]: time=2024-08-14T20:39:19.298-07:00 level=INFO source=types.go:105 msg="inference compute" id=> Loga Aug 14 21:02:33 gpu01 systemd[1]: ollama.service: Consumed 6.913s CPU time. [62/8875] Aug 14 21:02:33 gpu01 systemd[1]: Started Ollama Service. Aug 14 21:02:33 gpu01 ollama[808132]: 2024/08/14 21:02:33 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVI CE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://10.10.2 6.188:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA _MODELS:/opt/ollama/models/ OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https ://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http:/ /0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:fals e OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.695-07:00 level=INFO source=images.go:782 msg="total blobs: 0" Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.696-07:00 level=INFO source=images.go:790 msg="total unused blobs rem oved: 0" Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.696-07:00 level=INFO source=routes.go:1172 msg="Listening on 10.10.26 .188:11434 (version 0.3.6)" Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=INFO source=payload.go:30 msg="extracting embedded fi les" dir=/tmp/ollama120779224/runners Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp u file=build/linux/x86_64/cpu/bin/ollama_llama_server.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp u_avx file=build/linux/x86_64/cpu_avx/bin/ollama_llama_server.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cp u_avx2 file=build/linux/x86_64/cpu_avx2/bin/ollama_llama_server.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu da_v11 file=build/linux/x86_64/cuda_v11/bin/libcublas.so.11.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu da_v11 file=build/linux/x86_64/cuda_v11/bin/libcublasLt.so.11.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu da_v11 file=build/linux/x86_64/cuda_v11/bin/libcudart.so.11.0.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=cu da_v11 file=build/linux/x86_64/cuda_v11/bin/ollama_llama_server.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=ro cm_v60102 file=build/linux/x86_64/rocm_v60102/bin/deps.txt.gz Aug 14 21:02:33 gpu01 ollama[808132]: time=2024-08-14T21:02:33.697-07:00 level=DEBUG source=payload.go:182 msg=extracting variant=ro cm_v60102 file=build/linux/x86_64/rocm_v60102/bin/ollama_llama_server.gz Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo und" file=/tmp/ollama120779224/runners/cpu/ollama_llama_server Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo und" file=/tmp/ollama120779224/runners/cpu_avx/ollama_llama_server Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo und" file=/tmp/ollama120779224/runners/cpu_avx2/ollama_llama_server Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo und" file=/tmp/ollama120779224/runners/cuda_v11/ollama_llama_server Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:71 msg="availableServers : fo und" file=/tmp/ollama120779224/runners/rocm_v60102/ollama_llama_server Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11 rocm_v60102 cpu cpu_avx cpu_avx2]" Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=payload.go:45 msg="Override detection lo gic by setting OLLAMA_LLM_LIBRARY" Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler " Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.044-07:00 level=INFO source=gpu.go:204 msg="looking for compatible GP Us" Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:90 msg="searching for GPU discove ry libraries for NVIDIA" Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:472 msg="Searching for GPU librar y" name=libcuda.so* Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.045-07:00 level=DEBUG source=gpu.go:491 msg="gpu library search" glob s="[/libcuda.so** /usr/local/cuda*/targets/*/lib/libcuda.so* /usr/lib/*-linux-gnu/nvidia/current/libcuda.so* /usr/lib/*-linux-gnu/li bcuda.so* /usr/lib/wsl/lib/libcuda.so* /usr/lib/wsl/drivers/*/libcuda.so* /opt/cuda/lib*/libcuda.so* /usr/local/cuda/lib*/libcuda.so * /usr/lib*/libcuda.so* /usr/local/lib*/libcuda.so*]" Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.046-07:00 level=DEBUG source=gpu.go:525 msg="discovered GPU libraries " paths="[/usr/lib/i386-linux-gnu/libcuda.so.535.183.01 /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01]" Aug 14 21:02:36 gpu01 ollama[808132]: library /usr/lib/i386-linux-gnu/libcuda.so.535.183.01 load err: /usr/lib/i386-linux-gnu/libcud a.so.535.183.01: wrong ELF class: ELFCLASS32 Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.047-07:00 level=DEBUG source=gpu.go:566 msg="skipping 32bit library" library=/usr/lib/i386-linux-gnu/libcuda.so.535.183.01 Aug 14 21:02:36 gpu01 ollama[808132]: CUDA driver version: 12.2 Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.061-07:00 level=DEBUG source=gpu.go:123 msg="detected GPUs" count=1 l ibrary=/usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01 Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] CUDA totalMem 12044 mb Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] CUDA freeMem 11919 mb Aug 14 21:02:36 gpu01 ollama[808132]: [GPU-838e39e8-08a3-37c0-85d9-66182a7927ba] Compute Capability 8.6 Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.129-07:00 level=DEBUG source=amd_linux.go:371 msg="amdgpu driver not detected /sys/module/amdgpu" Aug 14 21:02:36 gpu01 ollama[808132]: releasing cuda driver library Aug 14 21:02:36 gpu01 ollama[808132]: time=2024-08-14T21:02:36.129-07:00 level=INFO source=types.go:105 msg="inference compute" id=G PU-838e39e8-08a3-37c0-85d9-66182a7927ba library=cuda compute=8.6 driver=12.2 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" availab le="11.6 GiB" ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.4
GiteaMirror added the bug label 2026-04-22 08:57:39 -05:00
GiteaMirror commented 2026-04-22 08:57:41 -05:00
Author
Owner
Copy Link

@ACodingfreak commented on GitHub (Aug 15, 2024):

But if I run the serve command as shown below it works properly as shown below.
One major change is i can see the OLLAMA_MODELS path

$ sudo su - ollama -s /bin/bash -c '/usr/local/bin/ollama serve'
[sudo] password for codingfreak: 
2024/08/14 21:29:57 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-08-14T21:29:57.625-07:00 level=INFO source=images.go:782 msg="total blobs: 5"
time=2024-08-14T21:29:57.643-07:00 level=INFO source=images.go:790 msg="total unused blobs removed: 0"
time=2024-08-14T21:29:57.644-07:00 level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11434 (version 0.3.6)"
time=2024-08-14T21:29:57.644-07:00 level=WARN source=assets.go:89 msg="process still running, skipping" pid=2236 path=/tmp/ollama719788881/ollama.pid
time=2024-08-14T21:29:57.644-07:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama1752088433/runners
time=2024-08-14T21:29:59.957-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [rocm_v60102 cpu cpu_avx cpu_avx2 cuda_v11]"
time=2024-08-14T21:29:59.957-07:00 level=INFO source=gpu.go:204 msg="looking for compatible GPUs"
time=2024-08-14T21:30:00.029-07:00 level=INFO source=types.go:105 msg="inference compute" id=GPU-838e39e8-08a3-37c0-85d9-66182a7927ba library=cuda compute=8.6 driver=12.2 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" available="11.6 GiB"

$ ollama --version 
ollama version is 0.3.6
<!-- gh-comment-id:2290571766 --> @ACodingfreak commented on GitHub (Aug 15, 2024): But if I run the serve command as shown below it works properly as shown below. One major change is i can see the OLLAMA_MODELS path ``` $ sudo su - ollama -s /bin/bash -c '/usr/local/bin/ollama serve' [sudo] password for codingfreak: 2024/08/14 21:29:57 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-08-14T21:29:57.625-07:00 level=INFO source=images.go:782 msg="total blobs: 5" time=2024-08-14T21:29:57.643-07:00 level=INFO source=images.go:790 msg="total unused blobs removed: 0" time=2024-08-14T21:29:57.644-07:00 level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11434 (version 0.3.6)" time=2024-08-14T21:29:57.644-07:00 level=WARN source=assets.go:89 msg="process still running, skipping" pid=2236 path=/tmp/ollama719788881/ollama.pid time=2024-08-14T21:29:57.644-07:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama1752088433/runners time=2024-08-14T21:29:59.957-07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [rocm_v60102 cpu cpu_avx cpu_avx2 cuda_v11]" time=2024-08-14T21:29:59.957-07:00 level=INFO source=gpu.go:204 msg="looking for compatible GPUs" time=2024-08-14T21:30:00.029-07:00 level=INFO source=types.go:105 msg="inference compute" id=GPU-838e39e8-08a3-37c0-85d9-66182a7927ba library=cuda compute=8.6 driver=12.2 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" available="11.6 GiB" $ ollama --version ollama version is 0.3.6 ```
GiteaMirror commented 2026-04-22 08:57:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 15, 2024):

Environment="OLLAMA_HOST=10.10.26.188"

The server is configured to bind to a specific IP address, the client uses a default of localhost. I'm assuming this has been set to allow connections from different devices. Either set this to OLLAMA_HOST=0.0.0.0 in ollama.service, or add export OLLAMA_HOST=10.10.26.188 to your .bashrc.

<!-- gh-comment-id:2290775912 --> @rick-github commented on GitHub (Aug 15, 2024): > Environment="OLLAMA_HOST=10.10.26.188" The server is configured to bind to a specific IP address, the client uses a default of `localhost`. I'm assuming this has been set to allow connections from different devices. Either set this to `OLLAMA_HOST=0.0.0.0` in ollama.service, or add `export OLLAMA_HOST=10.10.26.188` to your .bashrc.
GiteaMirror commented 2026-04-22 08:57:42 -05:00
Author
Owner
Copy Link

@ACodingfreak commented on GitHub (Aug 15, 2024):

Well this is the ipaddress of the server i.e. 10.10.26.188.

I have modified the ipaddress to 0.0.0.0 and restarted ollama.service

Aug 15 06:14:21 gpu01 systemd[1]: ollama.service: Consumed 8.129s CPU time.                                                         
Aug 15 06:14:21 gpu01 systemd[1]: Started Ollama Service.                                                                           
Aug 15 06:14:21 gpu01 ollama[60589]: 2024/08/15 06:14:21 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVIC
E_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:
11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODEL
S:/opt/ollama/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost http
s://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http:
//0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"

And it works fine now.

<!-- gh-comment-id:2291286097 --> @ACodingfreak commented on GitHub (Aug 15, 2024): Well this is the ipaddress of the server i.e. 10.10.26.188. I have modified the ipaddress to 0.0.0.0 and restarted ollama.service ``` Aug 15 06:14:21 gpu01 systemd[1]: ollama.service: Consumed 8.129s CPU time. Aug 15 06:14:21 gpu01 systemd[1]: Started Ollama Service. Aug 15 06:14:21 gpu01 ollama[60589]: 2024/08/15 06:14:21 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVIC E_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0: 11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODEL S:/opt/ollama/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost http s://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http: //0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" ``` And it works fine now.
GiteaMirror commented 2026-04-22 08:57:43 -05:00
Author
Owner
Copy Link

@ouening commented on GitHub (Nov 17, 2024):

I got the same error after I upgrade nvidia cuda and driver. My ollama version is 0.4.2. In ollama.service I have set

Environment="OLLAMA_HOST=0.0.0.0:11434"
Environment="OLLAMA_ORIGINS=*"

ollama list not worked. But I can still use ollama service from remote.

<!-- gh-comment-id:2481098415 --> @ouening commented on GitHub (Nov 17, 2024): I got the same error after I upgrade nvidia cuda and driver. My ollama version is 0.4.2. In ollama.service I have set ``` Environment="OLLAMA_HOST=0.0.0.0:11434" Environment="OLLAMA_ORIGINS=*" ``` `ollama lis`t not worked. But I can still use ollama service from remote.
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#29760
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?