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 #8151] cudart initialization failure on ppc64le (AlmaLinux/RHEL8) with ollama-0.1.31-1.1 #30963

New Issue
Open
opened 2026-04-22 11:00:19 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 11:00:19 -05:00
Owner
Copy Link

Originally created by @Bekbo01 on GitHub (Dec 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8151

What is the issue?

I’m encountering an issue running ollama-0.1.31-1.1 on a ppc64le system with AlmaLinux (RHEL8). The application fails to initialize CUDA runtime libraries, resulting in cudart init failure: 35 errors.

Environment Details:

OS: AlmaLinux (RHEL8 compatible)
Architecture: ppc64le
ollama version: 0.1.31-1.1
CUDA environment:
CUDA libraries are located under /usr/local/cuda/lib64/ and /usr/local/cuda-12.4/lib64/.
The CUDA runtime library found: libcudart.so.12.4.99.
Logs and Error Output:

time=2024-12-18T11:04:06.900+05:00 level=INFO source=gpu.go:115 msg="Detecting GPU type"
time=2024-12-18T11:04:06.900+05:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*"
time=2024-12-18T11:04:06.903+05:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/usr/local/cuda/lib64/libcudart.so.12.4.99 /usr/local/cuda-12.4/lib64/libcudart.so.12.4.99]"
time=2024-12-18T11:04:06.910+05:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.99: cudart init failure: 35"
time=2024-12-18T11:04:06.910+05:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /usr/local/cuda-12.4/lib64/libcudart.so.12.4.99: cudart init failure: 35"

any guidance on resolving the cudart init failure: 35 error?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @Bekbo01 on GitHub (Dec 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8151 ### What is the issue? I’m encountering an issue running ollama-0.1.31-1.1 on a ppc64le system with AlmaLinux (RHEL8). The application fails to initialize CUDA runtime libraries, resulting in cudart init failure: 35 errors. Environment Details: OS: AlmaLinux (RHEL8 compatible) Architecture: ppc64le ollama version: 0.1.31-1.1 CUDA environment: CUDA libraries are located under /usr/local/cuda/lib64/ and /usr/local/cuda-12.4/lib64/. The CUDA runtime library found: libcudart.so.12.4.99. Logs and Error Output: ``` time=2024-12-18T11:04:06.900+05:00 level=INFO source=gpu.go:115 msg="Detecting GPU type" time=2024-12-18T11:04:06.900+05:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*" time=2024-12-18T11:04:06.903+05:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/usr/local/cuda/lib64/libcudart.so.12.4.99 /usr/local/cuda-12.4/lib64/libcudart.so.12.4.99]" time=2024-12-18T11:04:06.910+05:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.99: cudart init failure: 35" time=2024-12-18T11:04:06.910+05:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /usr/local/cuda-12.4/lib64/libcudart.so.12.4.99: cudart init failure: 35" ``` any guidance on resolving the cudart init failure: 35 error? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 11:00:19 -05:00
GiteaMirror commented 2026-04-22 11:00:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 18, 2024):

Error 35 normally means the driver is too old.

<!-- gh-comment-id:2550830878 --> @rick-github commented on GitHub (Dec 18, 2024): Error 35 normally means the driver is too old.
GiteaMirror commented 2026-04-22 11:00:21 -05:00
Author
Owner
Copy Link

@ALutz273 commented on GitHub (Jan 7, 2025):

More Details -> https://github.com/ollama/ollama/pull/7777

<!-- gh-comment-id:2575507131 --> @ALutz273 commented on GitHub (Jan 7, 2025): More Details -> https://github.com/ollama/ollama/pull/7777
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#30963
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?