Docker Model Runner v1.2.6

What's Changed

🚀 Features

• Add an optional CommandModifier for backend runner processes (#1003) @mat007
• Pin llama.cpp version per release, allow pulling latest on demand, and make llama.cpp a deferred backend on macOS/Windows (#737) @doringeman
• Rewrite dmr as a standalone, engine-independent binary (#996) @ericcurtin
• Show size of model when using docker model search (#988) @KeeTraxx
• Add helper + tests for SyncDockerConfigToContainer (#947) @areebahmeddd

🐛 Bug Fixes

• Add Pascal GPU architecture support to llama.cpp build (#986) @lohitkolluri

📦 Dependencies

• Bump llama.cpp version for macOS and Windows (#1002) @docker
• Bump llama.cpp for Linux (#1001) @doringeman
• Bump llama.cpp to b9879 (#997) @docker
• Bump llamacpp to b9859 (#995) @krissetto
• Bump llama.cpp to b9837 (#990) @docker

🔧 Maintenance

• Pin actions to commit SHAs, drop 3p release action (#1000) @docker
• Update configure show command description and documentation (#928) @Montana

Full Changelog: v1.2.5...v1.2.6