Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package ollama for openSUSE:Factory checked in at 2026-03-03 15:32:20 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/ollama (Old) and /work/SRC/openSUSE:Factory/.ollama.new.29461 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "ollama" Tue Mar 3 15:32:20 2026 rev:56 rq:1336014 version:0.17.5 Changes: -------- --- /work/SRC/openSUSE:Factory/ollama/ollama.changes 2026-01-29 17:48:58.163583841 +0100 +++ /work/SRC/openSUSE:Factory/.ollama.new.29461/ollama.changes 2026-03-03 15:33:20.379016021 +0100 @@ -1,0 +2,94 @@ +Tue Mar 3 08:11:10 UTC 2026 - Adrian Schröter <[email protected]> + +- Update to version 0.17.5: + New models + - Qwen3.5: the small Qwen 3.5 model series is now available in + 0.8B, 2B, 4B and 9B parameter sizes. + What's Changed + - Fixed crash in Qwen 3.5 models when split over GPU & CPU + - Fixed issue where Qwen 3.5 models would repeat themselves due + to no presence penalty (note: you may have to redownload the + qwen3.5 models: ollama pull qwen3.5:35b for example) + - ollama run --verbose will now show peak memory usage when using + Ollama's MLX engine + - Fixed memory issues and crashes in MLX runner + - Fixed issue where Ollama would not be able to run models + imported from Qwen3.5 GGUF files + +------------------------------------------------------------------- +Sat Feb 28 15:54:51 UTC 2026 - Eyad Issa <[email protected]> + +- Add fix-mlxrunner-tests.diff: disable compiling MLX tests +- Update to version 0.17.4: + * New Models: Qwen 3.5, LFM 2 + * Tool call indices will now be included in parallel tool calls +- Update to version 0.17.3: + * Fixed issue where tool calls in the Qwen 3 and Qwen 3.5 model + families would not be parsed correctly if emitted during + thinking +- Update to version 0.17.2: + * No notable changes +- Update to version 0.17.1: + * Nemotron architecture support in Ollama's engine + * Improved LFM2 and LFM2.5 models in Ollama's engine +- Update to version 0.17.0: + * OpenClaw can now be installed and configured automatically via + Ollama: ollama launch openclaw + * Improved tokenizer performance +- Update to version 0.16.3: + * New ollama launch cline added for the Cline CLI + * ollama launch <integration> will now always show the model + picker +- Update to version 0.16.2: + * ollama launch claude now supports searching the web when using + :cloud models + * New setting in Ollama's app makes it easier to disable cloud + models for sensitive and private tasks where data cannot leave + your computer. For Linux or when running ollama serve manually, + set OLLAMA_NO_CLOUD=1. + * Fixed issue where experimental image generation models would + not run in 0.16.0 and 0.16.1 +- Update to version 0.16.1: + * Image generation models will now respect the + OLLAMA_LOAD_TIMEOUT variable +- Update to version 0.16.0: + * New Models: GLM-5; MiniMax-M2.5 + * New `ollama` command + * Launch Pi with ollama launch pi + * Ctrl+G will now allow for editing text prompts in a text + editor when running a model +- Update to version 0.15.6: + * Fixed context limits when running ollama launch droid + * ollama launch will now download missing models instead of + erroring + * Fixed bug where ollama launch claude would cause context + compaction when providing images +- Update to version 0.15.5: + * New models: Qwen3-Coder-Next, GLM-OCR + * ollama launch can now be provided arguments, for example + ollama launch claude -- --resume + * ollama launch will now work run subagents when using ollama + launch claude + * Ollama will now set context limits for a set of models when + using ollama launch opencode + * Sub-agent support for ollama launch for planning, deep + research, and similar tasks + * ollama signin will now open a browser window to make signing + in easier + * Ollama will now default to the following context lengths based + on VRAM: < 24 GiB VRAM: 4,096 context; 24-48 GiB VRAM: 32,768 + context; >= 48 GiB VRAM: 262,144 context + * Fixed off by one error when using num_predict in the API + * Fixed issue where tokens from a previous sequence would be + returned when hitting num_predict +- Update to version 0.15.4: + * ollama launch openclaw will now enter the standard OpenClaw + onboarding flow if this has not yet been completed. +- Update to version 0.15.3: + * Renamed ollama launch clawdbot to ollama launch openclaw to + reflect the project's new name + * Improved tool calling for Ministral models + * ollama launch will now use the value of OLLAMA_HOST when + running it + +------------------------------------------------------------------- Old: ---- build.specials.obscpio ollama-0.15.2.tar.gz New: ---- fix-mlxrunner-tests.diff ollama-0.17.5.tar.gz ----------(New B)---------- New: - Add fix-mlxrunner-tests.diff: disable compiling MLX tests - Update to version 0.17.4: ----------(New E)---------- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ ollama.spec ++++++ --- /var/tmp/diff_new_pack.QVCM2f/_old 2026-03-03 15:33:21.815075507 +0100 +++ /var/tmp/diff_new_pack.QVCM2f/_new 2026-03-03 15:33:21.819075673 +0100 @@ -35,7 +35,7 @@ %define cuda_version %{cuda_version_major}-%{cuda_version_minor} Name: ollama -Version: 0.15.2 +Version: 0.17.5 Release: 0 Summary: Tool for running AI models on-premise License: MIT @@ -45,6 +45,7 @@ Source2: %{name}.service Source3: %{name}-user.conf Source4: sysconfig.%{name} +Patch0: fix-mlxrunner-tests.diff BuildRequires: cmake >= 3.24 BuildRequires: git-core BuildRequires: ninja ++++++ fix-mlxrunner-tests.diff ++++++ diff --git a/x/mlxrunner/mlx/generator/main.go b/x/mlxrunner/mlx/generator/main.go index a98046a..05771d4 100644 --- a/x/mlxrunner/mlx/generator/main.go +++ b/x/mlxrunner/mlx/generator/main.go @@ -1,3 +1,5 @@ +//go:build mlx + package main import ( ++++++ ollama-0.15.2.tar.gz -> ollama-0.17.5.tar.gz ++++++ /work/SRC/openSUSE:Factory/ollama/ollama-0.15.2.tar.gz /work/SRC/openSUSE:Factory/.ollama.new.29461/ollama-0.17.5.tar.gz differ: char 13, line 1 ++++++ vendor.tar.zstd ++++++ Binary files /var/tmp/diff_new_pack.QVCM2f/_old and /var/tmp/diff_new_pack.QVCM2f/_new differ
