GitLab

Bump llama.cpp to b2276

Refine container image build script

Log unexpected server errors checking for update

This should unmask some failure modes that likely
show up in app logs as unmarshal errors

Allow overriding the platform, image name, and tag latest for
standard and rocm images.

* read iogpu.wired_limit_mb on macOS

Fix for https://github.com/ollama/ollama/issues/1826

* improved determination of available vram on macOS

read the recommended maximal vram on macOS via Metal API

* Removed macOS-specific logging

* Remove logging from gpu_darwin.go

* release Core Foundation object

fixes a possible memory leak

specfied -> specified

Remove unused GPT4all
Use nomic-embed-text as embedded model
Fix a deprecation warning (__call__)

remove format private key

this is unnecessary now that x/crypto/ssh.MarshalPrivateKey has been
added

Co-authored-by: bennhuang <bennhuang@tencent.com>

- Enchanted is now supported for desktop on macOS

Update install.sh success message

* remove `-w -s` linker flags on windows

* use `zip` for windows installer compression

Co-authored-by: bo.sun <bo.sun@cotticoffee.com>