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 #12366] run gemma3:12b Error: 500 Internal Server Error: llama runner process has terminated #70274

New Issue
Closed
opened 2026-05-04 20:55:06 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 20:55:06 -05:00
Owner
Copy Link

Originally created by @1574802103 on GitHub (Sep 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12366

What is the issue?

C:\Users\zhang>ollama run gemma3:12b
Error: 500 Internal Server Error: llama runner process has terminated: CUDA errorC:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.0

Originally created by @1574802103 on GitHub (Sep 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12366 ### What is the issue? C:\Users\zhang>ollama run gemma3:12b Error: 500 Internal Server Error: llama runner process has terminated: CUDA errorC:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.0
GiteaMirror added the bug label 2026-05-04 20:55:06 -05:00
GiteaMirror commented 2026-05-04 20:55:09 -05:00
Author
Owner
Copy Link

@1574802103 commented on GitHub (Sep 22, 2025):

C:\Users\zhang>ollama run gemma3:12b
Error: 500 Internal Server Error: llama runner process has terminated: CUDA error: invalid argument

C:\Users\zhang>ollama run gemma3:12b
Error: 500 Internal Server Error: llama runner process has terminated: CUDA error: invalid argument
current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667
current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667
cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
CUDA error: invalid argument
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
CUDA error: invalid argument
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667
cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
CUDA error: invalid argument
current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667
cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error

<!-- gh-comment-id:3317628395 --> @1574802103 commented on GitHub (Sep 22, 2025): C:\Users\zhang>ollama run gemma3:12b Error: 500 Internal Server Error: llama runner process has terminated: CUDA error: invalid argument C:\Users\zhang>ollama run gemma3:12b Error: 500 Internal Server Error: llama runner process has terminated: CUDA error: invalid argument current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667 current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667 cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2)) CUDA error: invalid argument C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2)) current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667 C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2)) CUDA error: invalid argument C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667 cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2)) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error CUDA error: invalid argument current device: 0, in function ggml_backend_cuda_buffer_set_tensor at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:667 cudaMemcpyAsync((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2)) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:84: CUDA error
GiteaMirror commented 2026-05-04 20:55:09 -05:00
Author
Owner
Copy Link

@therealkenc commented on GitHub (Sep 22, 2025):

"Same here"

Adding this env fixed it for me: OLLAMA_LLM_LIBRARY=cuda_v13

<!-- gh-comment-id:3317866909 --> @therealkenc commented on GitHub (Sep 22, 2025): "Same here" Adding this env fixed it for me: `OLLAMA_LLM_LIBRARY=cuda_v13`
GiteaMirror commented 2026-05-04 20:55:09 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Sep 22, 2025):

Can you please post the full log with OLLAMA_DEBUG=1?

If setting OLLAMA_LLM_LIBRARY solves the issue then it might be the same as https://github.com/ollama/ollama/issues/11211, which is caused overlapping installations of old and new versions and can be solved by a full reinstall.

<!-- gh-comment-id:3320667607 --> @jessegross commented on GitHub (Sep 22, 2025): Can you please post the full log with OLLAMA_DEBUG=1? If setting OLLAMA_LLM_LIBRARY solves the issue then it might be the same as https://github.com/ollama/ollama/issues/11211, which is caused overlapping installations of old and new versions and can be solved by a full reinstall.
GiteaMirror commented 2026-05-04 20:55:10 -05:00
Author
Owner
Copy Link

@1574802103 commented on GitHub (Sep 23, 2025):

卸载ollama 重新装就好了 感谢 jessegross

<!-- gh-comment-id:3322051429 --> @1574802103 commented on GitHub (Sep 23, 2025): 卸载ollama 重新装就好了 感谢 [jessegross](https://github.com/jessegross)
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#70274
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?