github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 13:42:25 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8582] ollama version is 0.5.7-0-ga420a45-dirty #5546

New Issue
Closed
opened 2026-04-12 16:48:21 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 16:48:21 -05:00
Owner
Copy Link

Originally created by @Mario4272 on GitHub (Jan 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8582

What is the issue?

Can we talk about how to fix this?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.7

Originally created by @Mario4272 on GitHub (Jan 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8582 ### What is the issue? Can we talk about how to fix this? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-12 16:48:21 -05:00
GiteaMirror commented 2026-04-12 16:48:22 -05:00
Author
Owner
Copy Link

@lescieur commented on GitHub (Jan 30, 2025):

root@chat admin]# ollama -v
ollama version is 0.5.7

--

uname -r

4.18.0-553.22.1.el8_10.x86_64

cat /etc/os-release

NAME="Rocky Linux"
VERSION="8.10 (Green Obsidian)"
ID="rocky"
ID_LIKE="rhel centos fedora"
VERSION_ID="8.10"
PLATFORM_ID="platform:el8"
PRETTY_NAME="Rocky Linux 8.10 (Green Obsidian)"

[root@chat admin]# nvidia-smi
Thu Jan 30 12:03:41 2025
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.256.02 Driver Version: 470.256.02 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Tesla K20c Off | 00000000:01:00.0 Off | 0 |
| 30% 27C P8 13W / 225W | 3MiB / 4743MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+

[root@chat admin]# nvidia-smi -L
GPU 0: Tesla K20c (UUID: GPU-e39b6686-367b-8403-2dfb-6acb0953f376)

Jan 30 11:52:18 chat ollama[26466]: device count 1
Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.375-06:00 level=DEBUG source=gpu.go:134 msg="detected GPUs" count=1 library=/usr/lib64/libcuda.so.470.256.02
Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] CUDA totalMem 4743 mb
Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] CUDA freeMem 4685 mb
Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] Compute Capability 3.5
Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=gpu.go:318 msg="[0] CUDA GPU is too old. Compute Capability detected: 3.5"
Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered"
Jan 30 11:52:18 chat ollama[26466]: releasing cuda driver library
Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx compute="" driver=0.0 name="" total="31.1 GiB" available="30.0 GiB"

Would it be possible to workaround the compatibility issue?

Ollama supports Nvidia GPUs with compute capability 5.0+ << Nvidia Tesla K20 not listed here.
https://github.com/ollama/ollama/blob/main/docs/gpu.md

<!-- gh-comment-id:2625223893 --> @lescieur commented on GitHub (Jan 30, 2025): root@chat admin]# ollama -v ollama version is 0.5.7 -- # uname -r 4.18.0-553.22.1.el8_10.x86_64 --- # cat /etc/os-release NAME="Rocky Linux" VERSION="8.10 (Green Obsidian)" ID="rocky" ID_LIKE="rhel centos fedora" VERSION_ID="8.10" PLATFORM_ID="platform:el8" PRETTY_NAME="Rocky Linux 8.10 (Green Obsidian)" --- [root@chat admin]# nvidia-smi Thu Jan 30 12:03:41 2025 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 470.256.02 Driver Version: 470.256.02 CUDA Version: 11.4 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 Tesla K20c Off | 00000000:01:00.0 Off | 0 | | 30% 27C P8 13W / 225W | 3MiB / 4743MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | No running processes found | +-----------------------------------------------------------------------------+ --- [root@chat admin]# nvidia-smi -L GPU 0: Tesla K20c (UUID: GPU-e39b6686-367b-8403-2dfb-6acb0953f376) --- Jan 30 11:52:18 chat ollama[26466]: device count 1 Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.375-06:00 level=DEBUG source=gpu.go:134 msg="detected GPUs" count=1 library=/usr/lib64/libcuda.so.470.256.02 Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] CUDA totalMem 4743 mb Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] CUDA freeMem 4685 mb Jan 30 11:52:18 chat ollama[26466]: [GPU-e39b6686-367b-8403-2dfb-6acb0953f376] Compute Capability 3.5 Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=gpu.go:318 msg="[0] CUDA GPU is too old. Compute Capability detected: 3.5" Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered" Jan 30 11:52:18 chat ollama[26466]: releasing cuda driver library Jan 30 11:52:18 chat ollama[26466]: time=2025-01-30T11:52:18.433-06:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx compute="" driver=0.0 name="" total="31.1 GiB" available="30.0 GiB" Would it be possible to workaround the compatibility issue? Ollama supports Nvidia GPUs with compute capability 5.0+ << Nvidia Tesla K20 not listed here. https://github.com/ollama/ollama/blob/main/docs/gpu.md
GiteaMirror commented 2026-04-12 16:48:23 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Jan 30, 2025):

@lescieur your issue doesn't look related. Please open a separate issue

@Mario4272 Where did you download Ollama from? The 0.5.7 release archive ollama-linux-amd64.tgz has version set to 0.5.7

<!-- gh-comment-id:2625709918 --> @mxyng commented on GitHub (Jan 30, 2025): @lescieur your issue doesn't look related. Please open a separate issue @Mario4272 Where did you download Ollama from? The [0.5.7](https://github.com/ollama/ollama/releases/tag/v0.5.7) release archive [ollama-linux-amd64.tgz](https://github.com/ollama/ollama/releases/download/v0.5.7/ollama-linux-amd64.tgz) has version set to 0.5.7
GiteaMirror commented 2026-04-12 16:48:23 -05:00
Author
Owner
Copy Link

@Arakade commented on GitHub (Feb 6, 2025):

I see the same but am using AMD GPU on Linux (Ubuntu 24.04.1 LTS). Pulled from docker.
@Mario4272 are you using docker? I'd hazard it's in the image (not checked myself).

Logs from pull (in case useful to know hashes):

> docker pull ollama/ollama
Using default tag: latest
latest: Pulling from ollama/ollama
6414378b6477: Already exists
ce386310af0b: Pull complete
434f39e9aa8e: Pull complete
bbc15f5291c8: Pull complete
Digest: sha256:7e672211886f8bd4448a98ed577e26c816b9e8b052112860564afaa2c105800e
Status: Downloaded newer image for ollama/ollama:latest
docker.io/ollama/ollama:latest

> docker pull ollama/ollama:rocm
rocm: Pulling from ollama/ollama
6414378b6477: Already exists
65a431633b1b: Pull complete
f271062961b2: Pull complete
18fea989b928: Pull complete
b9dfadf1ed0c: Pull complete
Digest: sha256:d05b7eefc8d8309b47377a6ac301a7f2c9e468ba13f3ef1c64dd4f51cd5151e8
Status: Downloaded newer image for ollama/ollama:rocm
docker.io/ollama/ollama:rocm
<!-- gh-comment-id:2638350317 --> @Arakade commented on GitHub (Feb 6, 2025): I see the same but am using AMD GPU on Linux (Ubuntu 24.04.1 LTS). Pulled from docker. @Mario4272 are you using docker? I'd hazard it's in the image (not checked myself). Logs from pull (in case useful to know hashes): ``` > docker pull ollama/ollama Using default tag: latest latest: Pulling from ollama/ollama 6414378b6477: Already exists ce386310af0b: Pull complete 434f39e9aa8e: Pull complete bbc15f5291c8: Pull complete Digest: sha256:7e672211886f8bd4448a98ed577e26c816b9e8b052112860564afaa2c105800e Status: Downloaded newer image for ollama/ollama:latest docker.io/ollama/ollama:latest > docker pull ollama/ollama:rocm rocm: Pulling from ollama/ollama 6414378b6477: Already exists 65a431633b1b: Pull complete f271062961b2: Pull complete 18fea989b928: Pull complete b9dfadf1ed0c: Pull complete Digest: sha256:d05b7eefc8d8309b47377a6ac301a7f2c9e468ba13f3ef1c64dd4f51cd5151e8 Status: Downloaded newer image for ollama/ollama:rocm docker.io/ollama/ollama:rocm ```
GiteaMirror commented 2026-04-12 16:48:24 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Feb 7, 2025):

this appears to be a bug with the 0.5.7 build artifact where it didn't set version correctly. the version is mostly cosmetic and should not have any adverse effects. it should be fixed in the next release

<!-- gh-comment-id:2641550700 --> @mxyng commented on GitHub (Feb 7, 2025): this appears to be a bug with the 0.5.7 build artifact where it didn't set version correctly. the version is mostly cosmetic and should not have any adverse effects. it should be fixed in the next release
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#5546
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?