Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package ollama for openSUSE:Factory checked in at 2026-11-13 18:33:02 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/ollama (Old) and /work/SRC/openSUSE:Factory/.ollama.new.1251 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "ollama" Fri Nov 13 18:33:02 2026 rev:73 rq:1397135 version:0.40.16 Changes: -------- --- /work/SRC/openSUSE:Factory/ollama/ollama.changes 2026-10-23 20:30:19.452679693 +0200 +++ /work/SRC/openSUSE:Factory/.ollama.new.1251/ollama.changes 2026-11-13 18:37:18.818335358 +0100 @@ -1,0 +2,84 @@ +Tue Nov 10 07:40:35 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.16 + * Add Ripple Preview, a 65B dense model built for agentic coding + * ollama launch claude always routes Claude Code to the + selected model + * ollama launch explains when a cloud model has been retired + * /v1/responses respects truncation and no longer silently + truncates by default + * /v1/models returns an empty list instead of null when no + models are installed + * Updated llama.cpp + * Release notes: https://github.com/ollama/ollama/releases/tag/v0.40.16 +- Update generated using pbuild-ai + +------------------------------------------------------------------- +Fri Nov 6 11:27:12 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.15 + * Add Xiaomi MiMo mimo-v2.6, a 9B model for code and agents + * Add AutoTrust decision models in 9b, 35b, and 27b-vl sizes + that return choices, yes/no probabilities, and ratings + * ollama launch supports Kimi Code CLI, migrates kimi-cli setups + * ollama launch fills in Pi's model list automatically + * Recurrent and vision GGUF models can serve concurrent requests + * Qwen3 and Qwen3.5 models support long-context (YaRN) scaling + * Running ollama with no arguments opens the welcome launcher + * Release notes: https://github.com/ollama/ollama/releases/tag/v0.40.15 +- Update generated using pbuild-ai + +------------------------------------------------------------------- +Wed Nov 4 07:56:23 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.14 + * ollama launch claude applies model output token limit + * cloud models no longer hit the 128k default cap + * /api/chat decodes compressed cloud web search responses + * OpenAI endpoints keep packaged sampler defaults + * omitted temperature/top_p now use model values + * /v1/responses preserves readable input content + * preserves prior assistant refusals in input + * ollama launch codex verifies ChatGPT routing + * reports a clear error when routing is unavailable + * Release notes: https://github.com/ollama/ollama/releases/tag/v0.40.14 +- Update generated using pbuild-ai + +------------------------------------------------------------------- +Thu Oct 29 07:37:19 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.13 + * LFM3 models run on Linux + * lfm3-audio/lfm3-omni support text-to-speech +- Update generated using pbuild-ai + +------------------------------------------------------------------- +Wed Oct 28 08:11:33 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.12 + * Keep more detail in small images for Gemma 4 + * Support OpenCode v2 in ollama launch + * Fix Kimi CLI tool-only assistant turns + * Update llama.cpp +- Update generated using pbuild-ai + +------------------------------------------------------------------- +Sun Oct 25 08:58:39 UTC 2026 - Adrian Schröter <[email protected]> + +- Updated to version 0.40.11 + * Generate speech on macOS + * ollama run plays text or replies aloud + * /v1/audio/speech can stream audio + * Add d3 decision models from vLLM Semantic Router + * d3 classifies, answers yes/no, or scores options + * d3 available in 2B, 4B, 9B, and 27B sizes + * SynapShift first contributed in PR #19173 +- Updated to version 0.40.10 + * Add NVIDIA Nemotron 3.5 Bolt E4B + * Gemma 4-based vision-language model + * Fast local conversations, image understanding, tool use + * Supports a 128K-token context window + * Includes DFlash draft for speculative decoding +- Update generated using pbuild-ai + +------------------------------------------------------------------- Old: ---- ollama-0.40.9.tar.gz New: ---- ollama-0.40.16.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ ollama.spec ++++++ --- /var/tmp/diff_new_pack.0vvwh4/_old 2026-11-13 18:37:21.199436169 +0100 +++ /var/tmp/diff_new_pack.0vvwh4/_new 2026-11-13 18:37:21.201436254 +0100 @@ -23,9 +23,9 @@ %global jobs 4 %endif -%global llama_cpp_version b11803 -%global mlx_version bebd6422f8db88d56e6220520a35bcd146f823f8 -%global mlx_c_version a341b4925024b88b2c593468f16e12f5e17315da +%global llama_cpp_version b12111 +%global mlx_version 54a70511f4ea151378d03b657a4fdd823386ea38 +%global mlx_c_version 57731b00e8bed710e0750e7356da9f18f8eb3e20 %{bcond_with cuda} %if 0%{?suse_version} >= 1610 @@ -82,7 +82,7 @@ %define cuda_version %{cuda_version_major}-%{cuda_version_minor} Name: ollama -Version: 0.40.9 +Version: 0.40.16 Release: 0 Summary: Tool for running AI models on-premise License: MIT ++++++ _agents.obscpio ++++++ ++++++ _scmsync.obsinfo ++++++ --- /var/tmp/diff_new_pack.0vvwh4/_old 2026-11-13 18:37:21.351442605 +0100 +++ /var/tmp/diff_new_pack.0vvwh4/_new 2026-11-13 18:37:21.355442774 +0100 @@ -1,5 +1,5 @@ -mtime: 1792742322 -commit: e4bad929b2a305200f186e67cc85e3f2a725aaa4218f28e96f9fcbe5f37cb037 +mtime: 1794296631 +commit: 9c5daea08b8da221c6fef007d9d2c260b335e478495e52db5aa43f0b271319b4 url: https://src.opensuse.org/AI/ollama.git revision: main ++++++ build.specials.obscpio ++++++ ++++++ build.specials.obscpio ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/.gitignore new/.gitignore --- old/.gitignore 1970-01-01 01:00:00.000000000 +0100 +++ new/.gitignore 2026-11-10 08:43:51.000000000 +0100 @@ -0,0 +1,17 @@ +*.obscpio +*.osc +_build.* +.pbuild +.assets +ollama +llama.cpp +mlx +mlx-c + +*.obsinfo +binaries +_service:* +*.orig +*.rej +*~ +osc-collab.* ++++++ llama.cpp-main.tar.xz ++++++ /work/SRC/openSUSE:Factory/ollama/llama.cpp-main.tar.xz /work/SRC/openSUSE:Factory/.ollama.new.1251/llama.cpp-main.tar.xz differ: char 15, line 1 ++++++ mlx-c-main.tar.xz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/mlx-c/CMakeLists.txt new/mlx-c/CMakeLists.txt --- old/mlx-c/CMakeLists.txt 2026-10-12 12:57:58.000000000 +0200 +++ new/mlx-c/CMakeLists.txt 2026-10-14 17:02:47.000000000 +0200 @@ -8,7 +8,7 @@ # ----------------------------- Configuration ----------------------------- if(NOT MLX_C_VERSION) - set(MLX_C_VERSION 0.6.0) + set(MLX_C_VERSION 0.7.0) endif() option(BUILD_SHARED_LIBS "Build mlx C as a shared library" OFF) diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/mlx-c/docs/src/conf.py new/mlx-c/docs/src/conf.py --- old/mlx-c/docs/src/conf.py 2026-10-12 12:57:58.000000000 +0200 +++ new/mlx-c/docs/src/conf.py 2026-10-14 17:02:47.000000000 +0200 @@ -10,7 +10,7 @@ project = "MLX C" copyright = "2023-2026, MLX Contributors" author = "MLX Contributors" -version = "0.6.0" +version = "0.7.0" release = version # -- General configuration --------------------------------------------------- ++++++ mlx-main.tar.xz ++++++ ++++ 2096 lines of diff (skipped) ++++++ ollama-0.40.9.tar.gz -> ollama-0.40.16.tar.gz ++++++ /work/SRC/openSUSE:Factory/ollama/ollama-0.40.9.tar.gz /work/SRC/openSUSE:Factory/.ollama.new.1251/ollama-0.40.16.tar.gz differ: char 19, line 1 ++++++ vendor.tar.gz ++++++ /work/SRC/openSUSE:Factory/ollama/vendor.tar.gz /work/SRC/openSUSE:Factory/.ollama.new.1251/vendor.tar.gz differ: char 13, line 1
