Colima v0.10.1

v0.10.1macOSLinux
Added 1
  • Support for Docker Model Runner as an AI model runner backend
Changed 3
  • Docker Model Runner is now the default AI model runner backend
  • The DOCKER_CONFIG environment variable is now respected
  • AI model runners refactored for improved functionality
Fixed 1
  • Model serving now chooses alternate available ports for API and webui when default ports are in use
Highlights

This is an incremental release with support for Docker Model Runner and improvements to the AI functionality introduced in v0.10.0.

Docker Model Runner

Colima now supports Docker Model Runner as an AI model runner backend. Docker Model Runner is now the default due to its simpler requirements. However, Ramalama can still be used.

# run a model (uses docker runner by default)
colima model run gemma3

# serve a model, chat interface available at localhost:8080
colima model serve gemma3

# explicitly specify the runner
colima model run gemma3 --runner docker
colima model run gemma3 --runner ramalama

# set the runner at start time
colima start --model-runner ramalama

The runner can be configured via:

  • --runner flag on colima model commands
  • --model-runner flag at colima start
  • modelRunner in the configuration file
Other Updates
  • The DOCKER_CONFIG environment variable is now respected.
Commits
New Contributors

Full Changelog: https://github.com/abiosoft/colima/compare/v0.10.0...v0.10.1

View original

Upgraded? How did it go?

Discussion