Files
LocalAI/backend/cpp/ik-llama-cpp/patches/0002-clip-ggml-quantize-chunk-user-data.patch
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

12 lines
468 B
Diff

--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -2494,7 +2494,7 @@
}
new_data = work.data();
- new_size = ggml_quantize_chunk(new_type, f32_data, new_data, 0, n_elms/cur->ne[0], cur->ne[0], nullptr);
+ new_size = ggml_quantize_chunk(new_type, f32_data, new_data, 0, n_elms/cur->ne[0], cur->ne[0], nullptr, nullptr);
} else {
new_type = cur->type;
new_data = cur->data;