ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)

* ggml : move FP16 <-> FP32 stuff to ggml-impl.h

ggml-ci

* tests : fix ARM build

* ggml : explicitly initialize deprecated type traits

* ggml : add math.h to ggml-impl.h

* ggml : remove duplicate static assert macros

* ggml : prefix lookup tables with ggml_

ggml-ci

* ggml-impl : move extern "C" to start of file

1 files changed, 1 insertions, 1 deletions

diff --git a/llama.cpp b/llama.cpp
index a4340d52..e599917a 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1467,7 +1467,7 @@ static int32_t llama_kv_cache_cell_max(const struct llama_kv_cache & cache) {
 }
 
 static void llama_kv_cache_clear(struct llama_kv_cache & cache) {
-    for (int32_t i = 0; i < cache.size; ++i) {
+    for (int32_t i = 0; i < (int32_t) cache.size; ++i) {
         cache.cells[i].pos = -1;
         cache.cells[i].seq_id.clear();
     }