github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4391] pre-built binary doesn't work on Jeston with JP6 GA system #49255

New Issue
Closed
opened 2026-04-28 11:01:28 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 11:01:28 -05:00
Owner
Copy Link

Originally created by @TadayukiOkada on GitHub (May 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4391

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I get this error if I run the pre-built binary on Jetson Orin with JP6 GA system installed:
source=sched.go:339 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED\n current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1848\n 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)\nGGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:60: !\"CUDA error\""

I built ollama from source and it runs fine on JP6 system. Also, pre-built binaries were working on JP5.1.3 system.

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

No response

Originally created by @TadayukiOkada on GitHub (May 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4391 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I get this error if I run the pre-built binary on Jetson Orin with JP6 GA system installed: `source=sched.go:339 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED\n current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1848\n 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)\nGGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:60: !\"CUDA error\""` I built ollama from source and it runs fine on JP6 system. Also, pre-built binaries were working on JP5.1.3 system. ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-28 11:01:28 -05:00
GiteaMirror added the nvidia label 2026-04-28 11:02:47 -05:00
GiteaMirror commented 2026-04-28 11:02:53 -05:00
Author
Owner
Copy Link

@hangxingliu commented on GitHub (May 25, 2024):

I also encountered this issue today on my AGX Orin after I tried using the latest pre-built ollama. However, everything works great like the past if I use the binary built by myself.

Here are some diagnosis, I hope them could help you to fix this issue:

Ollama's journal logs: 20240525-ollama-error-logs.log

The model that I tested: llama3:8b

My hardware info:

 - Module: NVIDIA Jetson AGX Orin (64GB ram)
 - SoC: tegra234
 - CUDA Arch BIN: 8.7
 
 - Machine: aarch64
 - System: Linux
 - Distribution: Ubuntu 22.04 Jammy Jellyfish
 - Release: 5.15.122-tegra
 - Jetpack: 6.0 DP
 
 - Python: 3.10.12
 - CUDA: 12.2.140
 - cuDNN: 8.9.4.25
 - TensorRT: 8.6.2.3
<!-- gh-comment-id:2130634535 --> @hangxingliu commented on GitHub (May 25, 2024): I also encountered this issue today on my AGX Orin after I tried using the latest pre-built ollama. However, everything works great like the past if I use the binary built by myself. Here are some diagnosis, I hope them could help you to fix this issue: Ollama's journal logs: [20240525-ollama-error-logs.log](https://github.com/ollama/ollama/files/15440993/20240525-ollama-error-logs.log) The model that I tested: `llama3:8b` My hardware info: ``` - Module: NVIDIA Jetson AGX Orin (64GB ram) - SoC: tegra234 - CUDA Arch BIN: 8.7 - Machine: aarch64 - System: Linux - Distribution: Ubuntu 22.04 Jammy Jellyfish - Release: 5.15.122-tegra - Jetpack: 6.0 DP - Python: 3.10.12 - CUDA: 12.2.140 - cuDNN: 8.9.4.25 - TensorRT: 8.6.2.3 ```
GiteaMirror commented 2026-04-28 11:02:54 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 31, 2024):

We'll track Orin/JP6 support in #2408

<!-- gh-comment-id:2143034417 --> @dhiltgen commented on GitHub (May 31, 2024): We'll track Orin/JP6 support in #2408
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#49255
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?