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 #8920] Error: llama runner process has terminated: GGML_ASSERT(n_backends <= GGML_SCHED_MAX_BACKENDS) failed #5785

New Issue
Closed
opened 2026-04-12 17:07:33 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 17:07:33 -05:00
Owner
Copy Link

Originally created by @Jac-hunter on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8920

What is the issue?

How could I solve that issue?
Thanks!

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.7

Originally created by @Jac-hunter on GitHub (Feb 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8920 ### What is the issue? How could I solve that issue? Thanks! ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-12 17:07:33 -05:00
GiteaMirror commented 2026-04-12 17:07:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2025):

Server logs may aid in debugging.

<!-- gh-comment-id:2642278206 --> @rick-github commented on GitHub (Feb 7, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.
GiteaMirror commented 2026-04-12 17:07:35 -05:00
Author
Owner
Copy Link

@Zncl2222 commented on GitHub (Feb 7, 2025):

@Jac-hunter Are you using more than 15 GPUs? The default maximum number of devices supported by llama.cpp is 16 (15 GPUs + 1 CPU).

I encountered this issue as well and found a related discussion on llama.cpp: [discussion link](https://github.com/ggerganov/llama.cpp/discussions/11218).

I'm curious if there's a way to modify GGML_SCHED_MAX_BACKENDS in Ollama.

<!-- gh-comment-id:2642813730 --> @Zncl2222 commented on GitHub (Feb 7, 2025): @Jac-hunter Are you using more than 15 GPUs? The default maximum number of devices supported by llama.cpp is 16 (15 GPUs + 1 CPU). I encountered this issue as well and found a related discussion on llama.cpp: [[discussion link]](https://github.com/ggerganov/llama.cpp/discussions/11218)(https://github.com/ggerganov/llama.cpp/discussions/11218). I'm curious if there's a way to modify GGML_SCHED_MAX_BACKENDS in Ollama.
GiteaMirror commented 2026-04-12 17:07:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2025):

https://github.com/ollama/ollama/issues/7148#issuecomment-2402288910

GGML_SCHED_MAX_BACKENDS is a compile time setting.

<!-- gh-comment-id:2642817420 --> @rick-github commented on GitHub (Feb 7, 2025): https://github.com/ollama/ollama/issues/7148#issuecomment-2402288910 `GGML_SCHED_MAX_BACKENDS` is a compile time setting.
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#5785
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?