Merge commit 'bfdf581b8b2a3c8e999227a44dfa3e890f1038bd' into concedo_experimental

# Conflicts:
#	ggml/src/ggml-cuda/conv-transpose-1d.cu
#	ggml/src/ggml-hip/CMakeLists.txt
#	scripts/ui-assets.cmake

src/llama-model.cpp

@@ -1150,9 +1150,17 @@ struct llama_model::impl {
     std::vector<layer_dev> dev_layer;
 
     bool has_tensor_overrides;
+
+    std::vector<float> tensor_split_owned;
 };
 
 llama_model::llama_model(const llama_model_params & params) : params(params), pimpl(std::make_unique<impl>()) {
+    if (params.tensor_split != nullptr) {
+        // llama_model_params stores tensor_split as a borrowed pointer, but the model
+        // may need it later for tensor-parallel KV-cache split metadata.
+        pimpl->tensor_split_owned.assign(params.tensor_split, params.tensor_split + llama_max_devices());
+        this->params.tensor_split = pimpl->tensor_split_owned.data();
+    }
     pimpl->has_tensor_overrides = params.tensor_buft_overrides && params.tensor_buft_overrides[0].pattern;
 }