3 Commits

Author	SHA256	Message	Date
Loren Burkholder	8ef2b26afe	Accepting request 1168020 from home:bmwiedemann:branches:science:machinelearning ... Update to version 0.1.31: * Backport MacOS SDK fix from main * Apply 01-cache.diff * fix: workflows * stub stub * mangle arch * only generate on changes to llm subdirectory * only generate cuda/rocm when changes to llm detected * Detect arrow keys on windows (#3363) * add license in file header for vendored llama.cpp code (#3351) * remove need for `$VSINSTALLDIR` since build will fail if `ninja` cannot be found (#3350) * change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347) * malformed markdown link (#3358) * Switch runner for final release job * Use Rocky Linux Vault to get GCC 10.2 installed * Revert "Switch arm cuda base image to centos 7" * Switch arm cuda base image to centos 7 * Bump llama.cpp to b2527 * Fix ROCm link in `development.md` * adds ooo to community integrations (#1623) * Add cliobot to ollama supported list (#1873) * Add Dify.AI to community integrations (#1944) * enh: add ollero.nvim to community applications (#1905) * Add typechat-cli to Terminal apps (#2428) * add new Web & Desktop link in readme for alpaca webui (#2881) * Add LibreChat to Web & Desktop Apps (#2918) * Add Community Integration: OllamaGUI (#2927) * Add Community Integration: OpenAOE (#2946) * Add Saddle (#3178) * tlm added to README.md terminal section. (#3274) ... OBS-URL: https://build.opensuse.org/request/show/1168020 OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=7	2024-04-17 00:53:52 +00:00
Loren Burkholder	9c6d1dfa92	- Update to version 0.1.28: ... * 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	2024-03-06 23:53:38 +00:00
Guillaume GARDET	5a3ae9ab21	Accepting request 1150495 from home:LorenDB ... I've created a package for Ollama (https://ollama.com) so that users don't have to use an install script. I will point out that this does not have CUDA support or ROCm enabled; we won't be able to package CUDA for obvious reasons, and ROCm is currently not packaged in Factory. However, for basic CPU-enabled use, this is better than curling a random script from the interwebs :) OBS-URL: https://build.opensuse.org/request/show/1150495 OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=1	2024-02-26 09:11:49 +00:00