github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13858] CCCL headers have moved in CUDA 13.0 #9071

New Issue
Open
opened 2026-04-12 21:54:41 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:54:41 -05:00
Owner
Copy Link

Originally created by @kamenik on GitHub (Jan 23, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13858

What is the issue?

Problem

Ollama + x/z-image-turbo crashes with the following error:

Failed to compile kernel: mlx/backend/cuda/device/indexing.cuh(3): catastrophic error: cannot open source file \"cuda/std/tuple\

Problem cause

Starting with 13.0, the CCCL headers bundled with CUDA Toolkit install have moved to new top-level directories under ${CTK_ROOT}/include/cccl/

More details here:

https://developer.nvidia.com/blog/whats-new-and-important-in-cuda-toolkit-13-0/#cccl_headers_have_moved_in_cuda_130

Workaround

On Ubuntu 24.04, creating a symbolic link solved the issue:

sudo ln -s /usr/local/cuda/targets/x86_64-linux/include/cccl/cuda /usr/local/cuda/targets/x86_64-linux/include/cuda

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.14.3

Originally created by @kamenik on GitHub (Jan 23, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13858 ### What is the issue? **Problem** Ollama + x/z-image-turbo crashes with the following error: ``` Failed to compile kernel: mlx/backend/cuda/device/indexing.cuh(3): catastrophic error: cannot open source file \"cuda/std/tuple\ ``` **Problem cause** Starting with 13.0, the CCCL headers bundled with CUDA Toolkit install have moved to new top-level directories under ${CTK_ROOT}/include/cccl/ More details here: https://developer.nvidia.com/blog/whats-new-and-important-in-cuda-toolkit-13-0/#cccl_headers_have_moved_in_cuda_130 **Workaround** On Ubuntu 24.04, creating a symbolic link solved the issue: ```bash sudo ln -s /usr/local/cuda/targets/x86_64-linux/include/cccl/cuda /usr/local/cuda/targets/x86_64-linux/include/cuda ``` ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.14.3
GiteaMirror added the bug label 2026-04-12 21:54:41 -05:00
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#9071
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?