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 #6999] Jetson CUDA error #50944

New Issue
Closed
opened 2026-04-28 17:38:14 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 17:38:14 -05:00
Owner
Copy Link

Originally created by @jarek7777 on GitHub (Sep 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6999

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I' ve built Ollama from source to run with CUDA but unfortunately it doesn't start any more, I think since version 0.3.10 it's the same error. Before 0.3.10 everything was fine I was able to build ollama with CUDA and run any model, but now even smallest model 1b is crashing

I have the same Jetpack 6.0 with CUDA 12.2.140.

Error: llama runner process has terminated: CUDA error: the resource allocation failed
current device: 0, in function cublas_handle at ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:644
cublasCreate_v2(&cublas_handles[device])
ollama/llm/llama.cpp/ggml/src/ggml-cuda.cu:102: CUDA error

OS

Linux

GPU

Nvidia, Other

CPU

Other

Ollama version

0.3.12

Originally created by @jarek7777 on GitHub (Sep 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6999 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I' ve built Ollama from source to run with CUDA but unfortunately it doesn't start any more, I think since version 0.3.10 it's the same error. Before 0.3.10 everything was fine I was able to build ollama with CUDA and run any model, but now even smallest model 1b is crashing I have the same Jetpack 6.0 with CUDA 12.2.140. Error: llama runner process has terminated: CUDA error: the resource allocation failed current device: 0, in function cublas_handle at ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:644 cublasCreate_v2(&cublas_handles[device]) ollama/llm/llama.cpp/ggml/src/ggml-cuda.cu:102: CUDA error ### OS Linux ### GPU Nvidia, Other ### CPU Other ### Ollama version 0.3.12
GiteaMirror added the bugnvidialinux labels 2026-04-28 17:38:15 -05:00
GiteaMirror commented 2026-04-28 17:38:21 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 28, 2024):

These sorts of errors on Jetsons are usually the result of trying to use the discrete GPU (sbsa) cuda library instead of the Jetpack specific cuda library. Depending on how you're building/installing, you might have accidentally wound up with our dGPU cuda library in your path.

Once we get #6925 merged, our official builds will bundle the jetpack 5 and 6 libraries and wire things up at runtime correctly.

<!-- gh-comment-id:2381017957 --> @dhiltgen commented on GitHub (Sep 28, 2024): These sorts of errors on Jetsons are usually the result of trying to use the discrete GPU (sbsa) cuda library instead of the Jetpack specific cuda library. Depending on how you're building/installing, you might have accidentally wound up with our dGPU cuda library in your path. Once we get #6925 merged, our official builds will bundle the jetpack 5 and 6 libraries and wire things up at runtime correctly.
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 linux nvidia
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#50944
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?