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 #3306] No GPU found! #64072

New Issue
Closed
opened 2026-05-03 16:04:35 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 16:04:35 -05:00
Owner
Copy Link

Originally created by @InfoOfInfo on GitHub (Mar 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3306

What are you trying to do?

root@localhost:~# ollama serve

time=2024-03-23T11:28:06.617+05:30 level=INFO source=images.go:806 msg="total blobs: 0"

time=2024-03-23T11:28:06.682+05:30 level=INFO source=images.go:813 msg="total unused blobs removed: 0"

time=2024-03-23T11:28:06.685+05:30 level=INFO source=routes.go: 1110 msg="Listening on 127.0.0.1:11434 (version 0.1.29)" time=2024-03-23T11:28:06.686+05:30 level=INFO source=payload_common.go:112 msg="Extracting dynamic libraries to /tmp/ollama3763750206/runners..."

time=2024-03-23T11:28:14.668+05:30 level=INFO source=payload_common.go:139 msg="Dynamic LLM libraries [cpu cuda_v11]"

time=2024-03-23T11:28:14.668+05:30 level=INFO source=gpu.go:77 msg="Detecting GPU type"

time=2024-03-23T11:28:14.668+05:30 level=INFO source=gpu.go:191 msg="Searching for GPU management library libnvidia-ml.so"

time=2024-03-23T11:28:14.675+05:30 level=INFO source=gpu.go: 237 msg="Discovered GPU libraries: []"

time=2024-03-23T11:28:14.675+05:30 level=INFO source=cpu_common.go:18 msg="CPU does not have vector extensions"

time=2024-03-23T11:28:14.676+05:30 level=INFO source=routes.go:1133 msg="no GPU detected"

How should we solve this?

Guys i am on a very old Samsung tablets that God knows has what specs its sure is 3 years old and has 3gb ram and no graphics card. can you all crowdfund me to get me a some kind of a pc i am 17 yrs old. sure you know what it feels like.
proof
SAMSUNG TAB A7

What is the impact of not solving this?

I will study hard and make something that helps humanity.

Anything else?

No response

Originally created by @InfoOfInfo on GitHub (Mar 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3306 ### What are you trying to do? root@localhost:~# ollama serve time=2024-03-23T11:28:06.617+05:30 level=INFO source=images.go:806 msg="total blobs: 0" time=2024-03-23T11:28:06.682+05:30 level=INFO source=images.go:813 msg="total unused blobs removed: 0" time=2024-03-23T11:28:06.685+05:30 level=INFO source=routes.go: 1110 msg="Listening on 127.0.0.1:11434 (version 0.1.29)" time=2024-03-23T11:28:06.686+05:30 level=INFO source=payload_common.go:112 msg="Extracting dynamic libraries to /tmp/ollama3763750206/runners..." time=2024-03-23T11:28:14.668+05:30 level=INFO source=payload_common.go:139 msg="Dynamic LLM libraries [cpu cuda_v11]" time=2024-03-23T11:28:14.668+05:30 level=INFO source=gpu.go:77 msg="Detecting GPU type" time=2024-03-23T11:28:14.668+05:30 level=INFO source=gpu.go:191 msg="Searching for GPU management library libnvidia-ml.so" time=2024-03-23T11:28:14.675+05:30 level=INFO source=gpu.go: 237 msg="Discovered GPU libraries: []" time=2024-03-23T11:28:14.675+05:30 level=INFO source=cpu_common.go:18 msg="CPU does not have vector extensions" **time=2024-03-23T11:28:14.676+05:30 level=INFO source=routes.go:1133 msg="no GPU detected"** ### How should we solve this? Guys i am on a very old Samsung tablets that God knows has what specs its sure is 3 years old and has 3gb ram and no graphics card. can you all crowdfund me to get me a some kind of a pc i am 17 yrs old. sure you know what it feels like. proof SAMSUNG TAB A7 ### What is the impact of not solving this? I will study hard and make something that helps humanity. ### Anything else? _No response_
GiteaMirror commented 2026-05-03 16:04:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 23, 2024):

CPU does not have vector extensions

Our current GPU code is compiled with vector extensions (AVX) to ensure that if all layers don't fit within the GPU, we get reasonable performance from the layers that are processed by the CPU. We have another issue tracking adding support for older CPUs (and server CPUs) that don't have AVX. #2187

<!-- gh-comment-id:2016380295 --> @dhiltgen commented on GitHub (Mar 23, 2024): `CPU does not have vector extensions` Our current GPU code is compiled with vector extensions (AVX) to ensure that if all layers don't fit within the GPU, we get reasonable performance from the layers that are processed by the CPU. We have another issue tracking adding support for older CPUs (and server CPUs) that don't have AVX. #2187
GiteaMirror commented 2026-05-03 16:04:37 -05:00
Author
Owner
Copy Link

@navr32 commented on GitHub (Apr 7, 2024):

Hi ! When do you think be abble to give access to gpu to old processor without avx ?
I have test the dbzoo commit by build on my z800 2xXeon rtx3090 and this work very well !
Many thanks. Because as far as now i am unable to use Ollama with my gpu since you have add this test...perhaps adding one option when starting ollama serve to disable the avx check ? because with just my cpu it is very too slow ...

<!-- gh-comment-id:2041240445 --> @navr32 commented on GitHub (Apr 7, 2024): Hi ! When do you think be abble to give access to gpu to old processor without avx ? I have test the dbzoo commit by build on my z800 2xXeon rtx3090 and this work very well ! Many thanks. Because as far as now i am unable to use Ollama with my gpu since you have add this test...perhaps adding one option when starting ollama serve to disable the avx check ? because with just my cpu it is very too slow ...
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#64072
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?