Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package llamacpp for openSUSE:Factory checked in at 2026-10-17 21:28:00 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/llamacpp (Old) and /work/SRC/openSUSE:Factory/.llamacpp.new.3698736 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "llamacpp" Sat Oct 17 21:28:00 2026 rev:38 rq:1385570 version:0.7.0 Changes: -------- --- /work/SRC/openSUSE:Factory/llamacpp/llamacpp.changes 2026-10-15 17:08:52.039569765 +0200 +++ /work/SRC/openSUSE:Factory/.llamacpp.new.3698736/llamacpp.changes 2026-10-17 21:28:02.347483436 +0200 @@ -1,0 +2,14 @@ +Sat Oct 17 00:00:00 UTC 2026 - Eyad Issa <[email protected]> + +- Update to version 0.7.0 + * Add LiliCorr speculative decoding and MTP for GLM5-Next. + * Add MoE expert GPU cache (--moe-cache-mib) with multi-GPU + cache sharing. + * Add new model support: K2 Horizon, Prism Bonsai 2, + EmbeddingGemma-2, LiquidAI d1/d1-omni, and vLLM decision models. + * Refactor server chat layer around common_chat_session and change + default listening port to 9931. + * Web UI gains full models manager; include b11669 Web UI asset. + * Update bundled GGML library to version 0.27.0. + +------------------------------------------------------------------- Old: ---- llama-b11429-ui.tar.gz llamacpp-0.6.0.tar.gz New: ---- llama-b11669-ui.tar.gz llamacpp-0.7.0.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ llamacpp.spec ++++++ --- /var/tmp/diff_new_pack.1BiEHE/_old 2026-10-17 21:28:03.635537249 +0200 +++ /var/tmp/diff_new_pack.1BiEHE/_new 2026-10-17 21:28:03.637537332 +0200 @@ -18,7 +18,7 @@ %global backend_dir %{_libdir}/ggml -%global upstream_build 11429 +%global upstream_build 11669 %global license_dir %{_datadir}/licenses %global llama_sover %{version} @@ -27,7 +27,7 @@ %global mtmd_sover %{llama_sover} %global mtmd_sover_suffix 0 -%global ggml_sover 0.26.0 +%global ggml_sover 0.27.0 %global ggml_sover_suffix 0 %if 0%{?suse_version} == 1500 @@ -43,7 +43,7 @@ %endif Name: llamacpp -Version: 0.6.0 +Version: 0.7.0 Release: 0 Summary: Inference of Meta's LLaMA model (and others) in pure C/C++ License: Apache-2.0 AND MIT AND BSD-2-Clause AND BSD-3-Clause AND ISC AND MPL-2.0 ++++++ llama-b11429-ui.tar.gz -> llama-b11669-ui.tar.gz ++++++ ++++ 7622 lines of diff (skipped) ++++++ llamacpp-0.6.0.tar.gz -> llamacpp-0.7.0.tar.gz ++++++ /work/SRC/openSUSE:Factory/llamacpp/llamacpp-0.6.0.tar.gz /work/SRC/openSUSE:Factory/.llamacpp.new.3698736/llamacpp-0.7.0.tar.gz differ: char 13, line 1
