Ettore Di Giacinto c0920f3273 fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature (#9531) ...

Bumps ik_llama.cpp pin to 16996aeab7. Upstream 286ce32...16996ae adds a
trailing `const struct quantize_user_data *` parameter to
`ggml_quantize_chunk` (PR ikawrakow/ik_llama.cpp#1677) but leaves
`examples/llava/clip.cpp` unchanged because their build has moved to
`examples/mtmd/`. LocalAI's prepare.sh still copies from
`examples/llava/`, so the dead 7-arg call reaches the grpc-server
compile and fails. Patch the call site to pass `nullptr` for the new
param.

Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash]

2026-04-24 13:07:26 +02:00

..

patches

fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature (#9531)

2026-04-24 13:07:26 +02:00

CMakeLists.txt

feat(backends): add ik-llama-cpp (#9326)

2026-04-12 13:51:28 +02:00

grpc-server.cpp

fix(ik-llama-cpp): adapt to common_grammar struct in sampling.h (#9512)

2026-04-23 13:45:06 +02:00

Makefile

fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature (#9531)

2026-04-24 13:07:26 +02:00

package.sh

feat(backends): add ik-llama-cpp (#9326)

2026-04-12 13:51:28 +02:00

prepare.sh

feat(backends): add ik-llama-cpp (#9326)

2026-04-12 13:51:28 +02:00

run.sh

feat(backends): add ik-llama-cpp (#9326)

2026-04-12 13:51:28 +02:00

utils.hpp

feat(backends): add ik-llama-cpp (#9326)

2026-04-12 13:51:28 +02:00