Script 'mail_helper' called by obssrc
Hello community,
here is the log from the commit of package llamacpp for openSUSE:Factory
checked in at 2025-04-20 09:36:21
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/llamacpp (Old)
and /work/SRC/openSUSE:Factory/.llamacpp.new.30101 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "llamacpp"
Sun Apr 20 09:36:21 2025 rev:6 rq:1271007 version:5158
Changes:
--------
--- /work/SRC/openSUSE:Factory/llamacpp/llamacpp.changes 2025-03-17
22:21:21.143900891 +0100
+++ /work/SRC/openSUSE:Factory/.llamacpp.new.30101/llamacpp.changes
2025-04-20 20:02:18.554778936 +0200
@@ -1,0 +2,51 @@
+Sat Apr 19 21:35:38 UTC 2025 - Eyad Issa <eyadlore...@gmail.com>
+
+- Remove convert_hf_to_gguf.py
+
+- Update to version 5158:
+ * Added support for new models:
+ ~ Llama 4 text-only
+ ~ IBM Granite 3.3 FIM tokens
+ ~ Qwen3 and Qwen3MoE
+ ~ BailingMoE (Ling)
+ ~ Trillion 7B model
+ ~ PLM GGUF Conversion & Inference
+ ~ RWKV v7 architecture
+ ~ GPT2, Bloom and CodeShell tied word embeddings
+ ~ EXAONE tied word embeddings
+ ~ DeepSeek V2/V3 MLA implementation
+ ~ Gemma 3 fixes and improvements
+ * Improved hardware acceleration support:
+ ~ Vulkan: Multiple optimizations for flash attention,
+ coopmat2, and shader performance
+ ~ OpenCL: Fixed profiling, improved Adreno GPU
+ identification, added multi and vision rope
+ * Performance optimizations:
+ ~ AVX512 implementation of GEMM for Q4_Kx8
+ ~ Faster SSM scan
+ ~ Block interleaving support for Q4_K quantization
+ on x86 AVX2
+ ~ PowerPC-specific optimizations
+ * Infrastructure improvements:
+ ~ Added ability to lazy-load safetensors remotely
+ without downloading
+ ~ Refactored downloading system to handle mmproj
+ with -hf option
+ ~ Added support for custom HF endpoint
+ ~ Added RPC backend with added commands
+ ~ Improved server with support for listening on unix
+ sockets
+ * Added image processing capabilities:
+ ~ Introduced libmtmd for image token handling
+ ~ Added image_manipulation and llava_uhd classes
+ ~ Fixed CPU-only CLIP image encoding
+ ~ Fixed clip loading GGUFs with missing description
+ * Bug fixes:
+ ~ Fixed compilation issues on various platforms
+ (s390x, POWER9, AIX, FreeBSD)
+ ~ Fixed memory leaks and allocation issues
+ ~ Fixed Ctrl+D/newline handling
+ ~ Fixed thread joining on server exit
+ ~ Fixed various backend-specific bugs
+
+-------------------------------------------------------------------
Old:
----
llamacpp-4889.obscpio
New:
----
llamacpp-5158.obscpio
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ llamacpp.spec ++++++
--- /var/tmp/diff_new_pack.dhBw9F/_old 2025-04-20 20:02:19.430815512 +0200
+++ /var/tmp/diff_new_pack.dhBw9F/_new 2025-04-20 20:02:19.434815679 +0200
@@ -17,7 +17,7 @@
Name: llamacpp
-Version: 4889
+Version: 5158
Release: 0
Summary: llama-cli tool to run inference using the llama.cpp library
License: MIT
@@ -141,16 +141,13 @@
# used for shader compilation only
rm %{buildroot}%{_bindir}/vulkan-shaders-gen
-
-# remove .py extension
-mv %{buildroot}%{_bindir}/convert_hf_to_gguf.py
%{buildroot}%{_bindir}/convert_hf_to_gguf
+# remove dev scripts
+rm %{buildroot}%{_bindir}/convert_hf_to_gguf.py
%files
%doc README.md
%license LICENSE
-%{_bindir}/convert_hf_to_gguf
-
%{_bindir}/llama-cli
%{_bindir}/llama-server
%{_bindir}/llama-bench
++++++ _service ++++++
--- /var/tmp/diff_new_pack.dhBw9F/_old 2025-04-20 20:02:19.490818017 +0200
+++ /var/tmp/diff_new_pack.dhBw9F/_new 2025-04-20 20:02:19.490818017 +0200
@@ -2,9 +2,9 @@
<service name="format_spec_file" mode="manual" />
<service name="obs_scm" mode="manual">
<param name="filename">llamacpp</param>
- <param name="url">https://github.com/ggerganov/llama.cpp.git</param>
+ <param name="url">https://github.com/ggml-org/llama.cpp.git</param>
<param name="scm">git</param>
- <param name="revision">b4889</param>
+ <param name="revision">b5158</param>
<param name="versionformat">@PARENT_TAG@</param>
<param name="versionrewrite-pattern">b(.*)</param>
<param name="changesgenerate">enable</param>
++++++ _servicedata ++++++
--- /var/tmp/diff_new_pack.dhBw9F/_old 2025-04-20 20:02:19.514819020 +0200
+++ /var/tmp/diff_new_pack.dhBw9F/_new 2025-04-20 20:02:19.514819020 +0200
@@ -1,6 +1,8 @@
<servicedata>
<service name="tar_scm">
<param
name="url">https://github.com/ggerganov/llama.cpp.git</param>
- <param
name="changesrevision">9f2250ba722738ec0e6ab684636268a79160c854</param></service></servicedata>
+ <param
name="changesrevision">9f2250ba722738ec0e6ab684636268a79160c854</param></service><service
name="tar_scm">
+ <param
name="url">https://github.com/ggml-org/llama.cpp.git</param>
+ <param
name="changesrevision">00137157fca3d17b90380762b4d7cc158d385bd3</param></service></servicedata>
(No newline at EOF)
++++++ llamacpp-4889.obscpio -> llamacpp-5158.obscpio ++++++
++++ 96493 lines of diff (skipped)
++++++ llamacpp.obsinfo ++++++
--- /var/tmp/diff_new_pack.dhBw9F/_old 2025-04-20 20:02:24.299018767 +0200
+++ /var/tmp/diff_new_pack.dhBw9F/_new 2025-04-20 20:02:24.331020103 +0200
@@ -1,5 +1,5 @@
name: llamacpp
-version: 4889
-mtime: 1741970480
-commit: 9f2250ba722738ec0e6ab684636268a79160c854
+version: 5158
+mtime: 1745078703
+commit: 00137157fca3d17b90380762b4d7cc158d385bd3
