Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/s390x.Dockerfile
#	.dockerignore
#	.github/workflows/docker.yml
#	.github/workflows/release.yml
#	docs/android.md
#	ggml/src/ggml-cpu/amx/mmq.cpp
#	ggml/src/ggml-hexagon/htp/ssm-conv.c
#	tests/peg-parser/test-gbnf-generation.cpp
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/server/README.md

src/llama-context.cpp

@@ -1166,6 +1166,10 @@ void llama_context::set_embeddings_layer_inp(uint32_t lid, bool enable) {
     sched_need_reserve = true;
 }
 
+void llama_context::set_nextn_layer_offset(int32_t offset) {
+    cparams.nextn_layer_offset = offset;
+}
+
 void llama_context::set_causal_attn(bool value) {
     LLAMA_LOG_DEBUG("%s: value = %d\n", __func__, value);
 
@@ -3709,6 +3713,10 @@ void llama_set_embeddings_layer_inp(llama_context * ctx, uint32_t lid, bool valu
     ctx->set_embeddings_layer_inp(lid, value);
 }
 
+void llama_set_nextn_layer_offset(llama_context * ctx, int32_t offset) {
+    ctx->set_nextn_layer_offset(offset);
+}
+
 llama_memory_t llama_get_memory(const struct llama_context * ctx) {
     if (!ctx) {
         return nullptr;