Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package llamacpp for openSUSE:Factory checked in at 2025-08-25 20:38:58 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/llamacpp (Old) and /work/SRC/openSUSE:Factory/.llamacpp.new.30751 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "llamacpp" Mon Aug 25 20:38:58 2025 rev:17 rq:1301212 version:6188 Changes: -------- --- /work/SRC/openSUSE:Factory/llamacpp/llamacpp.changes 2025-08-13 16:32:45.754034455 +0200 +++ /work/SRC/openSUSE:Factory/.llamacpp.new.30751/llamacpp.changes 2025-08-25 20:41:04.135558407 +0200 @@ -1,0 +2,19 @@ +Sun Aug 17 22:17:38 UTC 2025 - Eyad Issa <[email protected]> + +- Update to version 6188: + * Vulkan backend improvements: larger workgroups, optimized + argsort, fused adds, bounds checking, out-of-bounds and compile + warning fixes, performance logging. + * OpenCL backend: initial FA and mxfp4 support. + * Model support: vision LiquidAI LFM2-VL family, 18-layer Gemma + 3-270m model type. + * Common: fixed double BOS, improved chat templates, added + override-tensor and CPU MoE draft parameters. + * GGML: initial IBM zDNN backend, rope_multi update, conv_1d_dw + bug fix, block_iq4_nlx8 repack, improved Mistral integration. + * Server: SWA checkpoints, -td/-tbd parameters, harmony thought + message filtering. + * Perplexity: improved error hints and constraint reporting. + * GPT-OSS: harmony parsing implemented. + +------------------------------------------------------------------- Old: ---- llamacpp-6139.tar.gz New: ---- llamacpp-6188.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ llamacpp.spec ++++++ --- /var/tmp/diff_new_pack.pglQFW/_old 2025-08-25 20:41:04.847588237 +0200 +++ /var/tmp/diff_new_pack.pglQFW/_new 2025-08-25 20:41:04.851588404 +0200 @@ -20,7 +20,7 @@ %global backend_dir %{_libdir}/ggml Name: llamacpp -Version: 6139 +Version: 6188 Release: 0 Summary: Inference of Meta's LLaMA model (and others) in pure C/C++ License: MIT ++++++ llamacpp-6139.tar.gz -> llamacpp-6188.tar.gz ++++++ /work/SRC/openSUSE:Factory/llamacpp/llamacpp-6139.tar.gz /work/SRC/openSUSE:Factory/.llamacpp.new.30751/llamacpp-6188.tar.gz differ: char 16, line 1
