Merge commit '12ee1763a6f6130ce820a366d220bbadff54b818' into concedo_experimental

# Conflicts:
#	docs/backend/hexagon/README.md
#	docs/backend/hexagon/developer.md
#	examples/gen-docs/gen-docs.cpp
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	examples/sycl/run-llama2.sh
#	examples/sycl/run-llama3.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-run-llama3.bat
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-utils.h
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/htp-dma.c
#	ggml/src/ggml-hexagon/htp/htp-dma.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/transpose.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/snapdragon/adb/run-cli.sh
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md

src/llama-model-loader.cpp

@@ -466,6 +466,29 @@ namespace GGUFMeta {
         return get_key_or_arr(llm_kv(kid), result, n, required);
     }
 
+    bool llama_model_loader::get_key_or_arr(enum llm_kv kid, uint32_t & result, bool required) {
+        const std::string key = llm_kv(kid);
+
+        const int id = gguf_find_key(meta.get(), key.c_str());
+
+        if (id < 0) {
+            if (required) {
+                throw std::runtime_error(format("key not found in model: %s", key.c_str()));
+            }
+            return false;
+        }
+
+        // throw and error if type is an array
+        if (gguf_get_kv_type(meta.get(), id) == GGUF_TYPE_ARRAY) {
+            if (required) {
+                throw std::runtime_error(format("expected scalar, found array for key: %s", key.c_str()));
+            }
+            return false;
+        }
+
+        return get_key(key, result, required);
+    }
+
     // TODO: this is not very clever - figure out something better
     template bool llama_model_loader::get_key_or_arr<std::array<int, 4>>(enum llm_kv kid, std::array<int, 4> & result, uint32_t n, bool required);
     template bool llama_model_loader::get_key_or_arr<std::array<uint32_t, 512>>(enum llm_kv kid, std::array<uint32_t, 512> & result, uint32_t n, bool required);