Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package llamacpp for openSUSE:Factory checked in at 2025-05-30 14:32:23 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/llamacpp (Old) and /work/SRC/openSUSE:Factory/.llamacpp.new.25440 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "llamacpp" Fri May 30 14:32:23 2025 rev:9 rq:1280718 version:5516 Changes: -------- --- /work/SRC/openSUSE:Factory/llamacpp/llamacpp.changes 2025-05-20 12:19:58.581773369 +0200 +++ /work/SRC/openSUSE:Factory/.llamacpp.new.25440/llamacpp.changes 2025-05-30 17:23:42.995254374 +0200 @@ -1,0 +2,21 @@ +Tue May 27 22:51:38 UTC 2025 - Eyad Issa <eyadlore...@gmail.com> + +- Update to 5516: + * llama : remove llama_kv_cache_view API + * model : disable SWA for Phi models + * kv-cache : simplify the interface + * server : Add the endpoints /api/tags and /api/chat + * ggml : add ggml_gelu_erf() + * hparams : support models for which all layers use SWA + * opencl: fix couple crashes + * opencl: Add support for multiple devices + * mtmd : add ultravox audio input + * server : support audio input + * server: streaming of tool calls and thoughts when jinja is on + * mtmd : support Qwen 2.5 Omni + * ggml : riscv: add xtheadvector support + * opencl : various optimizations + * Full changelog: + https://github.com/ggml-org/llama.cpp/compare/b5426...b5516 + +------------------------------------------------------------------- Old: ---- llamacpp-5426.tar.gz New: ---- llamacpp-5516.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ llamacpp.spec ++++++ --- /var/tmp/diff_new_pack.wlC0AV/_old 2025-05-30 17:23:43.527276470 +0200 +++ /var/tmp/diff_new_pack.wlC0AV/_new 2025-05-30 17:23:43.527276470 +0200 @@ -17,9 +17,9 @@ Name: llamacpp -Version: 5426 +Version: 5516 Release: 0 -Summary: llama-cli tool to run inference using the llama.cpp library +Summary: Inference of Meta's LLaMA model (and others) in pure C/C++ License: MIT URL: https://github.com/ggml-org/llama.cpp Source: https://github.com/ggml-org/llama.cpp/archive/b%{version}/%{name}-%{version}.tar.gz ++++++ llamacpp-5426.tar.gz -> llamacpp-5516.tar.gz ++++++ /work/SRC/openSUSE:Factory/llamacpp/llamacpp-5426.tar.gz /work/SRC/openSUSE:Factory/.llamacpp.new.25440/llamacpp-5516.tar.gz differ: char 29, line 2
