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 #5100] Jetson - Alternating Errors (Timed Out & CUDA Error) When Trying to Use Ollama #65255

New Issue
Closed
opened 2026-05-03 20:13:39 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 20:13:39 -05:00
Owner
Copy Link

Originally created by @Vassar-HARPER-Project on GitHub (Jun 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5100

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When running ollama run commands (regardless of model, even for something small like gemma:2b, the command does not work properly and results in an error. However, after testing, the error seems to consistently alternate back and forth (swaps every time) between this output:
Error: timed out waiting for llama runner to start - progress 1.00 -

and this output:
Error: llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1905 cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0*ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1*ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP) GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:100: !"CUDA error"

I'm running on a Jetson AGX Orin with 32GB of memory.

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

0.1.44

Originally created by @Vassar-HARPER-Project on GitHub (Jun 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5100 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When running `ollama run` commands (regardless of model, even for something small like `gemma:2b`, the command does not work properly and results in an error. However, after testing, the error seems to consistently alternate back and forth (swaps every time) between this output: `Error: timed out waiting for llama runner to start - progress 1.00 -` and this output: `Error: llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1905 cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0*ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1*ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP) GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:100: !"CUDA error"` I'm running on a Jetson AGX Orin with 32GB of memory. ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version 0.1.44
GiteaMirror added the bugnvidia labels 2026-05-03 20:13:50 -05:00
GiteaMirror commented 2026-05-03 20:13:59 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 18, 2024):

I know @dhiltgen has been testing Ollama on the Jetsons, I'm not sure Ollama supports the AGX Orin yet.

<!-- gh-comment-id:2175871683 --> @jmorganca commented on GitHub (Jun 18, 2024): I know @dhiltgen has been testing Ollama on the Jetsons, I'm not sure Ollama supports the AGX Orin yet.
GiteaMirror commented 2026-05-03 20:14:02 -05:00
Author
Owner
Copy Link

@Vassar-HARPER-Project commented on GitHub (Jun 18, 2024):

I can tell you it has worked at some point in the past for this exact device, before a re-flash (factory reset, for all intents and purposes)

<!-- gh-comment-id:2176058527 --> @Vassar-HARPER-Project commented on GitHub (Jun 18, 2024): I can tell you it has worked at some point in the past for this exact device, before a re-flash (factory reset, for all intents and purposes)
GiteaMirror commented 2026-05-03 20:14:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

PR #4741 will add support for JetPack 5 and JetPack 6 devices in the official builds.

<!-- gh-comment-id:2176464371 --> @dhiltgen commented on GitHub (Jun 18, 2024): PR #4741 will add support for JetPack 5 and JetPack 6 devices in the official builds.
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 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#65255
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?