Merge commit '67e3f6f60155870d4b5ce727515aa81e5a7b4753' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	ci/run.sh
#	docs/backend/CANN.md
#	docs/backend/OPENCL.md
#	examples/batched/batched.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	src/llama-context.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp

src/llama-model.cpp

@@ -8076,12 +8076,17 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
     // add on pooling layer
     llm->build_pooling(cls, cls_b, cls_out, cls_out_b);
 
+    // add backend sampling layers (if any)
+    llm->build_sampling();
+
     // if the gguf model was converted with --sentence-transformers-dense-modules
     // there will be two additional dense projection layers
     // dense linear projections are applied after pooling
     // TODO: move reranking logic here and generalize
     llm->build_dense_out(dense_2_out_layers, dense_3_out_layers);
 
+    llm->res->set_outputs();
+
     return llm->res->get_gf();
 }