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 #12999] 运行模型无法在GPU上运行 #8607

New Issue
Closed
opened 2026-04-12 21:20:40 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 21:20:40 -05:00
Owner
Copy Link

Originally created by @wll0307 on GitHub (Nov 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12999

What is the issue?

运行ollama启动后没有办法加载GPU只能cpu，我是在更新失败后我还是用原先的版本就出现了这个问题

Relevant log output

(occ) root@jikimo-virtual-machine:/home/jikimo/code/2Dces# ollama serve
time=2025-11-07T16:48:08.678+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-11-07T16:48:08.678+08:00 level=INFO source=images.go:522 msg="total blobs: 0"
time=2025-11-07T16:48:08.678+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-07T16:48:08.678+08:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)"
time=2025-11-07T16:48:08.678+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-07T16:48:08.679+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32769"
time=2025-11-07T16:48:08.704+08:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="31.4 GiB" available="24.7 GiB"
time=2025-11-07T16:48:08.704+08:00 level=INFO source=routes.go:1619 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
^C(occ) root@jikimo-virtual-machine:/home/jikimo/code/2Dces# ollama -v
Warning: could not connect to a running Ollama instance
Warning: client version is 0.12.10

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.12.10

Originally created by @wll0307 on GitHub (Nov 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12999 ### What is the issue? 运行ollama启动后没有办法加载GPU只能cpu，我是在更新失败后我还是用原先的版本就出现了这个问题 ### Relevant log output ```shell (occ) root@jikimo-virtual-machine:/home/jikimo/code/2Dces# ollama serve time=2025-11-07T16:48:08.678+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-11-07T16:48:08.678+08:00 level=INFO source=images.go:522 msg="total blobs: 0" time=2025-11-07T16:48:08.678+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-07T16:48:08.678+08:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)" time=2025-11-07T16:48:08.678+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-07T16:48:08.679+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32769" time=2025-11-07T16:48:08.704+08:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="31.4 GiB" available="24.7 GiB" time=2025-11-07T16:48:08.704+08:00 level=INFO source=routes.go:1619 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" ^C(occ) root@jikimo-virtual-machine:/home/jikimo/code/2Dces# ollama -v Warning: could not connect to a running Ollama instance Warning: client version is 0.12.10 ``` ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.12.10
GiteaMirror added the bug label 2026-04-12 21:20:40 -05:00
GiteaMirror commented 2026-04-12 21:20:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 7, 2025):

Run the following and post the output;

OLLAMA_DEBUG=2 ollama serve

What GPU is in the machine?

<!-- gh-comment-id:3501517229 --> @rick-github commented on GitHub (Nov 7, 2025): Run the following and post the output; ``` OLLAMA_DEBUG=2 ollama serve ``` What GPU is in the machine?
GiteaMirror commented 2026-04-12 21:20:42 -05:00
Author
Owner
Copy Link

@wll0307 commented on GitHub (Nov 10, 2025):

运行以下命令并贴出输出结果；

OLLAMA_DEBUG=2 ollama serve

这台机器里用的是什么GPU？

3090的我在更新前是没出现任何问题，只是我更新失败后我没有选择继续更新，然后运行模型就开始出现加载模型就开始只显示cpu了

<!-- gh-comment-id:3509028573 --> @wll0307 commented on GitHub (Nov 10, 2025): > 运行以下命令并贴出输出结果； > > ``` > OLLAMA_DEBUG=2 ollama serve > ``` > > 这台机器里用的是什么GPU？ 3090的我在更新前是没出现任何问题，只是我更新失败后我没有选择继续更新，然后运行模型就开始出现加载模型就开始只显示cpu了
GiteaMirror commented 2026-04-12 21:20:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 10, 2025):

Run the following and post the output;

OLLAMA_DEBUG=2 ollama serve
<!-- gh-comment-id:3509032718 --> @rick-github commented on GitHub (Nov 10, 2025): Run the following and post the output; ``` OLLAMA_DEBUG=2 ollama serve ```
GiteaMirror commented 2026-04-12 21:20:43 -05:00
Author
Owner
Copy Link

@wll0307 commented on GitHub (Nov 10, 2025):

运行以下命令并贴出输出结果；

OLLAMA_DEBUG=2 ollama serve

谢谢了，感谢解决了，我更新了，可能是更新失败导致的是GPU没有获取

Image
<!-- gh-comment-id:3509246613 --> @wll0307 commented on GitHub (Nov 10, 2025): > 运行以下命令并贴出输出结果； > > ``` > OLLAMA_DEBUG=2 ollama serve > ``` 谢谢了，感谢解决了，我更新了，可能是更新失败导致的是GPU没有获取 <img width="716" height="154" alt="Image" src="https://github.com/user-attachments/assets/f665e582-1586-42d9-9f22-66d310499021" />
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#8607
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?