Ettore Di Giacinto 3b47122e54 feat(llama-cpp,turboquant): arm64 gcc-14 for SME variants + darwin cpu-all packaging ...

- arm64: ggml CPU_ALL_VARIANTS builds armv9.2 SME variants whose -march=...+sme
  is rejected by the Ubuntu 24.04 default gcc-13. Build the arm64 variants with
  gcc-14 (installed in the compile step). The host only selects a variant it
  actually supports at runtime, but every variant must still compile.
- darwin: scripts/build/llama-cpp-darwin.sh builds llama-cpp-cpu-all instead of
  the fallback binary, keeps Metal (GGML_METAL stays ON; --target ggml also builds
  ggml-metal). The per-microarch libggml-cpu-*.dylib are placed in the package
  root next to the binary (darwin has no bundled ld.so, so ggml's executable-dir
  scan looks there), while the other shared dylibs go in lib/ for DYLD_LIBRARY_PATH.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

2026-06-24 21:50:29 +00:00

..

apt-mirror.sh

feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650)

2026-05-03 23:50:13 +02:00

ik-llama-cpp-compile.sh

ci: refactor llama-cpp variant Dockerfiles to consume prebuilt base-grpc images (PR 2/2) (#9738)

2026-05-10 00:03:52 +02:00

install-base-deps.sh

feat(vulkan): make Vulkan backends self-contained on the GPU (#10404)

2026-06-19 17:16:33 +02:00

llama-cpp-compile.sh

feat(llama-cpp,turboquant): arm64 gcc-14 for SME variants + darwin cpu-all packaging

2026-06-24 21:50:29 +00:00

turboquant-compile.sh

feat(llama-cpp,turboquant): arm64 gcc-14 for SME variants + darwin cpu-all packaging

2026-06-24 21:50:29 +00:00