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 #13307] failed with status code 500: llama runner process has terminated: exit status 2 #55302

New Issue
Closed
opened 2026-04-29 08:48:16 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 08:48:16 -05:00
Owner
Copy Link

Originally created by @Riperjame on GitHub (Dec 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13307

What is the issue?

When I successfully downloaded and pulled the deepseek-r1:14b model, running it immediately gave an error: Ollama call failed with status code 500: llama runner process has terminated: exit status 2. Then I ran the deepseek-r1:8b model and found that the CPU usage was about 50% and the GPU 98%, which had never happened before.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @Riperjame on GitHub (Dec 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13307 ### What is the issue? When I successfully downloaded and pulled the deepseek-r1:14b model, running it immediately gave an error: Ollama call failed with status code 500: llama runner process has terminated: exit status 2. Then I ran the deepseek-r1:8b model and found that the CPU usage was about 50% and the GPU 98%, which had never happened before. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 08:48:16 -05:00
GiteaMirror commented 2026-04-29 08:48:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 3, 2025):

Server log will help in debugging.

<!-- gh-comment-id:3605971645 --> @rick-github commented on GitHub (Dec 3, 2025): [Server log](https://docs.ollama.com/troubleshooting) will help in debugging.
GiteaMirror commented 2026-04-29 08:48:20 -05:00
Author
Owner
Copy Link

@Riperjame commented on GitHub (Dec 4, 2025):

Resolved.
Here is what I encountered: after pulling the deepseek-r1:14b model, running it would immediately throw an error failed with status code 500: llama runner process has terminated: exit status 2. However, after pulling the deepseek-r1:8b model, it ran with CPU ~50% and GPU ~98%. This is clearly abnormal as it had never occurred before.
In the Ollama crash logs, I found the core cause of the error was graph_reserve: failed to allocate compute buffers + memory address exception (Exception0xc0000005). The issue stemmed from [context length set too high] + [GPU memory allocation policy conflict]: the default OLLAMA_CONTEXT_LENGTH=262144 is too large, whereas the 14B model only supports 131072 and the 16GB GPU memory cannot handle it.
So, I created the environment variable OLLAMA_CONTEXT_LENGTH=8192 and restarted Ollama, which solved the issue.

服务器日志有助于调试。

<!-- gh-comment-id:3611044789 --> @Riperjame commented on GitHub (Dec 4, 2025): Resolved. Here is what I encountered: after pulling the deepseek-r1:14b model, running it would immediately throw an error failed with status code 500: llama runner process has terminated: exit status 2. However, after pulling the deepseek-r1:8b model, it ran with CPU ~50% and GPU ~98%. This is clearly abnormal as it had never occurred before. In the Ollama crash logs, I found the core cause of the error was graph_reserve: failed to allocate compute buffers + memory address exception (Exception0xc0000005). The issue stemmed from [context length set too high] + [GPU memory allocation policy conflict]: the default OLLAMA_CONTEXT_LENGTH=262144 is too large, whereas the 14B model only supports 131072 and the 16GB GPU memory cannot handle it. So, I created the environment variable OLLAMA_CONTEXT_LENGTH=8192 and restarted Ollama, which solved the issue. > [服务器日志](https://docs.ollama.com/troubleshooting)有助于调试。
GiteaMirror commented 2026-04-29 08:48:22 -05:00
Author
Owner
Copy Link

@metal3d commented on GitHub (Dec 4, 2025):

OLLAMA_CONTEXT_LENGTH=8192

It didn't fix the problem for me

<!-- gh-comment-id:3611521303 --> @metal3d commented on GitHub (Dec 4, 2025): > OLLAMA_CONTEXT_LENGTH=8192 It didn't fix the problem for me
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#55302
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?