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 #14727] ollama generate images failed in cuda 13.1 #35283

New Issue
Open
opened 2026-04-22 19:40:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 19:40:52 -05:00
Owner
Copy Link

Originally created by @panmcai on GitHub (Mar 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14727

What is the issue?

How to reproduce this problem？

ollama run x/z-image-turbo:bf16 "a cat holding a sign that says hello world"

The result is "Error: 500 Internal Server Error: Post "http://127.0.0.1:40927/completion": EOF"

ollama serve repoted MLX error: Failed to compile kernel: nvrtc: error: failed to open libnvrtc-builtins.so.13.0.

My cuda version is V13.1.80

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @panmcai on GitHub (Mar 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14727 ### What is the issue? # How to reproduce this problem？ ollama run x/z-image-turbo:bf16 "a cat holding a sign that says hello world" The result is "Error: 500 Internal Server Error: Post "http://127.0.0.1:40927/completion": EOF" ollama serve repoted MLX error: Failed to compile kernel: nvrtc: error: failed to open libnvrtc-builtins.so.13.0. My cuda version is V13.1.80 ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 19:40:52 -05:00
GiteaMirror commented 2026-04-22 19:40:53 -05:00
Author
Owner
Copy Link

@sushilibdev commented on GitHub (Mar 9, 2026):

The issue is likely caused by the MLX build stage in the Dockerfile being pinned to CUDA 13.0, which creates a hard dependency on libnvrtc-builtins.so.13.0. Should we update the build environment to CUDA 13.1 to support newer drivers, or implement a symlink fallback in the Dockerfile to handle minor version mismatches?

<!-- gh-comment-id:4021751694 --> @sushilibdev commented on GitHub (Mar 9, 2026): The issue is likely caused by the MLX build stage in the Dockerfile being pinned to CUDA 13.0, which creates a hard dependency on libnvrtc-builtins.so.13.0. Should we update the build environment to CUDA 13.1 to support newer drivers, or implement a symlink fallback in the Dockerfile to handle minor version mismatches?
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#35283
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?