[GH-ISSUE #7372] crash after OLLAMA_MULTIUSER_CACHE=1 #30445

Closed
opened 2026-04-22 10:03:52 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @y-tor on GitHub (Oct 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7372

Originally assigned to: @jessegross on GitHub.

What is the issue?

When I start loading a model, such as granite3-dense, I get this error:

error: unknown argument: --multiuser-cache
usage: /usr/lib/ollama/runners/cuda_v12/ollama_llama_server [options]

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.14

Originally created by @y-tor on GitHub (Oct 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7372 Originally assigned to: @jessegross on GitHub. ### What is the issue? When I start loading a model, such as granite3-dense, I get this error: error: unknown argument: --multiuser-cache usage: /usr/lib/ollama/runners/cuda_v12/ollama_llama_server [options] ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.14
GiteaMirror added the bug label 2026-04-22 10:03:52 -05:00
Author
Owner

@jessegross commented on GitHub (Oct 28, 2024):

This is intended only for development use cases (which is why it was left undocumented). It won't work in the mode you are running it in.

<!-- gh-comment-id:2442859971 --> @jessegross commented on GitHub (Oct 28, 2024): This is intended only for development use cases (which is why it was left undocumented). It won't work in the mode you are running it in.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#30445