Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package llamacpp for openSUSE:Factory checked in at 2025-09-02 17:58:24 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/llamacpp (Old) and /work/SRC/openSUSE:Factory/.llamacpp.new.1977 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "llamacpp" Tue Sep 2 17:58:24 2025 rev:18 rq:1302234 version:6269 Changes: -------- --- /work/SRC/openSUSE:Factory/llamacpp/llamacpp.changes 2025-08-25 20:41:04.135558407 +0200 +++ /work/SRC/openSUSE:Factory/.llamacpp.new.1977/llamacpp.changes 2025-09-02 17:58:46.163624899 +0200 @@ -1,0 +2,25 @@ +Mon Aug 25 13:29:14 UTC 2025 - Eyad Issa <eyadlore...@gmail.com> + +- Update to version 6269: + * Model and conversion: support for Seed-OSS, GPT-OSS + response_format, interns1-mini, Ernie 4.5, gpt-oss type + strings, improved Mistral templates, new model conversion + tool/example with torch-cpu. + * Vulkan backend: multiple optimizations (rms_norm, mul_mat_id, + synchronization, conv2d, subgroup ops), new ops (exp, + conv_2d_dw f16, ggml_mean). + * GGML/CPU: added conv3d op, WebGPU quantization support, + Q5_0/Q5_1 on s390x, mxfp4 intrinsics on ppc64le. + * Server and chat: multimodal completion and embeddings + JSON support, improved OpenAI API compatibility and usage + statistics, disabled context shift by default, fixed ordering + of tasks, webui issues, debug assertions, clarified + reasoning_format. + * KV cache: unified handling improvements, support for reuse, + removal of deprecated APIs, simplifications. + * Miscellaneous: fixed logging of non-ASCII characters, removed + deprecated or unused code and build artifacts. + * Full commit log: + https://github.com/ggml-org/llama.cpp/compare/b6188...b6269 + +------------------------------------------------------------------- Old: ---- llamacpp-6188.tar.gz New: ---- llamacpp-6269.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ llamacpp.spec ++++++ --- /var/tmp/diff_new_pack.CB0s1V/_old 2025-09-02 17:58:46.911656378 +0200 +++ /var/tmp/diff_new_pack.CB0s1V/_new 2025-09-02 17:58:46.911656378 +0200 @@ -20,7 +20,7 @@ %global backend_dir %{_libdir}/ggml Name: llamacpp -Version: 6188 +Version: 6269 Release: 0 Summary: Inference of Meta's LLaMA model (and others) in pure C/C++ License: MIT ++++++ llamacpp-6188.tar.gz -> llamacpp-6269.tar.gz ++++++ /work/SRC/openSUSE:Factory/llamacpp/llamacpp-6188.tar.gz /work/SRC/openSUSE:Factory/.llamacpp.new.1977/llamacpp-6269.tar.gz differ: char 15, line 1
