Merge commit 'd6f3030047f85a98b009189e76f441fe818ea44d' into concedo_experimental

# Conflicts:
#	examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/amx/amx.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-buffer.cpp
#	ggml/src/ggml-virtgpu/ggml-backend.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	pyproject.toml
#	requirements/requirements-convert_legacy_llama.txt
#	requirements/requirements-tool_bench.txt
#	src/llama-model.cpp
#	src/llama.cpp
#	tests/test-llama-archs.cpp
#	tests/test-tokenizer-0.py
#	tests/test-tokenizer-random.py
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp

src/llama-memory-recurrent.cpp

@@ -1,5 +1,6 @@
 #include "llama-memory-recurrent.h"
 
+#include "ggml-backend.h"
 #include "llama-impl.h"
 #include "llama-io.h"
 #include "llama-batch.h"
@@ -91,8 +92,8 @@ llama_memory_recurrent::llama_memory_recurrent(
             throw std::runtime_error("failed to create ggml context for rs cache");
         }
 
-        ggml_tensor * r = ggml_new_tensor_1d(ctx, type_r, hparams.n_embd_r()*mem_size);
-        ggml_tensor * s = ggml_new_tensor_1d(ctx, type_s, hparams.n_embd_s()*mem_size);
+        ggml_tensor * r = ggml_new_tensor_2d(ctx, type_r, hparams.n_embd_r(), mem_size);
+        ggml_tensor * s = ggml_new_tensor_2d(ctx, type_s, hparams.n_embd_s(), mem_size);
         ggml_format_name(r, "cache_r_l%d", i);
         ggml_format_name(s, "cache_s_l%d", i);
         r_l[i] = r;