* Fix embeddings load model behavior (#2848)
* Add Community Integration: NextChat (#2780)
* prepend image tags (#2789)
* fix: print usedMemory size right (#2827)
* bump submodule to `87c91c07663b707e831c59ec373b5e665ff9d64a` (#2828)
* Add ollama user to video group
* Add env var so podman will map cuda GPUs
* Omit build date from gzip headers
* Log unexpected server errors checking for update
* Refine container image build script
* Bump llama.cpp to b2276
* Determine max VRAM on macOS using `recommendedMaxWorkingSetSize` (#2354)
* Update types.go (#2744)
* Update langchain python tutorial (#2737)
* no extra disk space for windows installation (#2739)
* clean up go.mod
* remove format/openssh.go
* Add Community Integration: Chatbox
* better directory cleanup in `ollama.iss`
* restore windows build flags and compression
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=6