Ettore Di Giacinto a62f53b6e1 fix(cachyllama): use portable ARM build ...

Avoid the CPU_ALL_VARIANTS SME matrix on ARM, where the Linux and Darwin backend toolchains fail to compile CachyLLaMA. Keep the existing variant build for x86 and use the fully linked fallback build for ARM.

Assisted-by: Codex:gpt-5 [systematic-debugging]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-09-28 03:02:23 +00:00

..

apt-mirror.sh

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

bonsai-compile.sh

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

cachyllama-compile.sh

fix(cachyllama): use portable ARM build

2026-09-28 03:02:23 +00:00

ik-llama-cpp-compile.sh

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

install-base-deps.sh

feat(sycl): make the intel llama.cpp backend self-contained on any host (#10991)

2026-07-31 23:39:53 +02:00

llama-cpp-build-target.sh

fix(rocm): stop building the ggml CPU variant matrix for hipblas llama.cpp (#11346)

2026-08-04 15:55:58 +02:00

llama-cpp-compile.sh

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

turboquant-build-target.sh

fix(sycl): stop building the ggml CPU variant matrix with icpx (#11321)

2026-08-03 19:00:00 +02:00

turboquant-compile.sh

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00