Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package ollama for openSUSE:Factory checked in at 2025-10-05 17:51:13 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/ollama (Old) and /work/SRC/openSUSE:Factory/.ollama.new.11973 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "ollama" Sun Oct 5 17:51:13 2025 rev:44 rq:1309021 version:0.12.3 Changes: -------- --- /work/SRC/openSUSE:Factory/ollama/ollama.changes 2025-08-08 15:13:38.992629016 +0200 +++ /work/SRC/openSUSE:Factory/.ollama.new.11973/ollama.changes 2025-10-05 17:51:35.904464045 +0200 @@ -1,0 +2,93 @@ +Sat Oct 4 18:37:31 UTC 2025 - Eyad Issa <[email protected]> + +- Update to version 0.12.3: + * New models: DeepSeek-V3.1-Terminus, Kimi K2-Instruct-0905 + * Fixed issue where tool calls provided as stringified JSON + would not be parsed correctly + * ollama push will now provide a URL to follow to sign in + * Fixed issues where qwen3-coder would output unicode characters + incorrectly + * Fix issue where loading a model with /load would crash +- Update to version 0.12.2: + * A new web search API is now available in Ollama + * Models with Qwen3's architecture including MoE now run in + Ollama's new engine + * Fixed issue where built-in tools for gpt-oss were not being + rendered correctly + * Support multi-regex pretokenizers in Ollama's new engine + * Ollama's new engine can now load tensors by matching a prefix + or suffix +- Update to version 0.12.1: + * New model: Qwen3 Embedding: state of the art open embedding + model by the Qwen team + * Qwen3-Coder now supports tool calling + * Fixed issue where Gemma3 QAT models would not output correct + tokens + * Fix issue where & characters in Qwen3-Coder would not be parsed + correctly when function calling + * Fixed issues where ollama signin would not work properly +- Update to version 0.12.0: + * Cloud models are now available in preview + * Models with the Bert architecture now run on Ollama's engine + * Models with the Qwen 3 architecture now run on Ollama's engine + * Fixed issue where models would not be imported correctly with + ollama create + * Ollama will skip parsing the initial <think> if provided in + the prompt for /api/generate +- Update to version 0.11.11: + * Improved memory usage when using gpt-oss + * Fixed error that would occur when attempting to import + safetensor files + * Improved memory estimates for hybrid and recurrent models + * Fixed error that would occur when when batch size was greater + than context length + * Flash attention & KV cache quantization validation fixes + * Add dimensions field to embed requests + * Enable new memory estimates in Ollama's new engine by default + * Ollama will no longer load split vision models in the Ollama engine + +------------------------------------------------------------------- +Tue Sep 9 12:33:54 UTC 2025 - Eyad Issa <[email protected]> + +- Update to version 0.11.10: + * Added support for EmbeddingGemma, a new open embedding model +- Update to version 0.11.9: + * Improved performance via overlapping GPU and CPU computations +- Update to version 0.11.8: + * gpt-oss now has flash attention enabled by default for systems + that support it + * Improved load times for gpt-oss + +------------------------------------------------------------------- +Mon Aug 25 21:33:35 UTC 2025 - Eyad Issa <[email protected]> + +- Update to version 0.11.7: + * DeepSeek-V3.1 is now available to run via Ollama. + * Fixed issue where multiple models would not be loaded on + CPU-only systems + * Ollama will now work with models who skip outputting the + initial <think> tag (e.g. DeepSeek-V3.1) + * Fixed issue where text would be emitted when there is no + opening <think> tag from a model + * Fixed issue where tool calls containing { or } would not be + parsed correctly + +- Update to version 0.11.6: + * Improved performance when using flash attention + * Fixed boundary case when encoding text using BPE + +- Update to version 0.11.5: + * Performance improvements for the gpt-oss models + * Improved memory management for scheduling models on GPUs, + leading to better VRAM utilization, model performance and less + out of memory errors. These new memory estimations can be + enabled with OLLAMA_NEW_ESTIMATES=1 ollama serve and will soon + be enabled by default. + * Improved multi-GPU scheduling and reduced VRAM allocation when + using more than 2 GPUs + * Fix error when parsing bad harmony tool calls + * OLLAMA_FLASH_ATTENTION=1 will also enable flash attention for + pure-CPU models + * Fixed OpenAI-compatible API not supporting reasoning_effort + +------------------------------------------------------------------- Old: ---- ollama-0.11.4.tar.gz New: ---- ollama-0.12.3.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ ollama.spec ++++++ --- /var/tmp/diff_new_pack.m1U6pq/_old 2025-10-05 17:51:36.828502628 +0200 +++ /var/tmp/diff_new_pack.m1U6pq/_new 2025-10-05 17:51:36.828502628 +0200 @@ -21,7 +21,7 @@ %endif Name: ollama -Version: 0.11.4 +Version: 0.12.3 Release: 0 Summary: Tool for running AI models on-premise License: MIT @@ -77,7 +77,10 @@ export GOFLAGS="${GOFLAGS} -v" -%cmake -UOLLAMA_INSTALL_DIR -DOLLAMA_INSTALL_DIR=%{_libdir}/ollama +%cmake \ + -UCMAKE_INSTALL_BINDIR -DCMAKE_INSTALL_BINDIR=%{_libdir}/ollama \ + -UOLLAMA_INSTALL_DIR -DOLLAMA_INSTALL_DIR=%{_libdir}/ollama \ + %{nil} %cmake_build cd .. @@ -118,10 +121,10 @@ %service_del_postun %{name}.service %files -%doc README.md %license LICENSE %{_docdir}/%{name} %{_bindir}/%{name} +%{_libdir}/%{name} %{_unitdir}/%{name}.service %{_sysusersdir}/%{name}-user.conf %{_prefix}/lib/ollama ++++++ ollama-0.11.4.tar.gz -> ollama-0.12.3.tar.gz ++++++ /work/SRC/openSUSE:Factory/ollama/ollama-0.11.4.tar.gz /work/SRC/openSUSE:Factory/.ollama.new.11973/ollama-0.12.3.tar.gz differ: char 16, line 1 ++++++ vendor.tar.zstd ++++++ Binary files /var/tmp/diff_new_pack.m1U6pq/_old and /var/tmp/diff_new_pack.m1U6pq/_new differ
