mirror of
https://github.com/getumbrel/umbrel-apps.git
synced 2026-11-22 05:51:35 +03:00
Update ollama to v0.40.2
This commit is contained in:
1 parent
d3e367c36b
commit
ed8d58812e
2 files changed
+5
-5
No files matched your search
@@ -8,7 +8,7 @@ services:
|
||||
PROXY_AUTH_ADD: "false"
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:0.40.1@sha256:69f27594d8127cb43db1edcafa5e2d3cd8f88bdbc54a2cf3ceb11b8d138a24b1
|
||||
image: ollama/ollama:0.40.2@sha256:b86366bb528bbf7f1424435d165028497a5b69bf6ddb4fa5a87102e2b79f44fb
|
||||
environment:
|
||||
OLLAMA_ORIGINS: "*"
|
||||
OLLAMA_CONTEXT_LENGTH: 8192
|
||||
|
||||
@@ -5,7 +5,7 @@ storage:
|
||||
name: Ollama
|
||||
tagline: Self-host open source AI models like DeepSeek-R1, Llama, and more
|
||||
category: ai
|
||||
version: "0.40.1"
|
||||
version: "0.40.2"
|
||||
port: 11434
|
||||
description: >-
|
||||
Ollama allows you to download and run advanced AI models directly on your own hardware. Self-hosting AI models ensures full control over your data and protects your privacy.
|
||||
@@ -43,9 +43,9 @@ permissions:
|
||||
- GPU
|
||||
releaseNotes: >-
|
||||
Key highlights in this release:
|
||||
- Proxies Ollama cloud usage and balance APIs through the server.
|
||||
- Removes the account step from CLI onboarding.
|
||||
- Includes fixes for model manifests, Windows Clef model loading, and MLX runtime handling.
|
||||
- Upgrades existing models in the background the first time they run for better llama.cpp performance and compatibility.
|
||||
- Keeps temporary backup copies of upgraded models so downgrading remains safe.
|
||||
- Fixes duplicate entries appearing in `ollama list` after model upgrades.
|
||||
|
||||
|
||||
Full release notes are available at https://github.com/ollama/ollama/releases/
|
||||
|
||||
Reference in new issue
Block a user