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 #3051] Error when disk with temp dirs (e.g. /tmp) is full #1876

New Issue
Closed
opened 2026-04-12 11:57:32 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 11:57:32 -05:00
Owner
Copy Link

Originally created by @hanaidong on GitHub (Mar 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3051

Originally assigned to: @dhiltgen on GitHub.

I tested it will start failed,
image

This causes the systemd to constantly restart this service and download many temporary files that will not be deleted yet

image

key error

Error: unable to initialize llm library copy payload llama.cpp/build/linux/x86_64/cuda_v11/lib/libcublasLt.so.11.gz: gzip: invalid checksum
Originally created by @hanaidong on GitHub (Mar 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3051 Originally assigned to: @dhiltgen on GitHub. I tested it will start failed, ![image](https://github.com/ollama/ollama/assets/139938824/69481726-35b0-4119-bfea-15295fee80ad) This causes the systemd to constantly restart this service and download many temporary files that will not be deleted yet ![image](https://github.com/ollama/ollama/assets/139938824/f1730daa-293b-49ee-b66e-a75cc02e41e2) key error ``` Error: unable to initialize llm library copy payload llama.cpp/build/linux/x86_64/cuda_v11/lib/libcublasLt.so.11.gz: gzip: invalid checksum ```
GiteaMirror added the bug label 2026-04-12 11:57:32 -05:00
GiteaMirror commented 2026-04-12 11:57:35 -05:00
Author
Owner
Copy Link

@aosan commented on GitHub (Mar 11, 2024):

Has this been installed with the curl -fsSL https://ollama.com/install.sh | sh as a regular user with sudo access?

Are you using a recent version of Ubuntu?

Your last error seems to be about CUDA version 11, currently at 12.x, is it installed correctly? nvcc --version should tell you more about your CUDA installation.

<!-- gh-comment-id:1988448415 --> @aosan commented on GitHub (Mar 11, 2024): Has this been installed with the `curl -fsSL https://ollama.com/install.sh | sh` as a regular user with sudo access? Are you using a recent version of Ubuntu? Your last error seems to be about CUDA version 11, currently at 12.x, is it installed correctly? ` nvcc --version` should tell you more about your CUDA installation.
GiteaMirror commented 2026-04-12 11:57:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 12, 2024):

We should harden the extraction logic to clean up after itself on error.

<!-- gh-comment-id:1992240960 --> @dhiltgen commented on GitHub (Mar 12, 2024): We should harden the extraction logic to clean up after itself on error.
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#1876
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?