Merge commit 'c945aaaef298ddb3eed72d36e45d6b3a2a1abd75' into concedo_experimental

# Conflicts:
#	.devops/cann.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	README.md
#	common/CMakeLists.txt
#	common/chat.cpp
#	docs/function-calling.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	models/templates/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.jinja
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/peg-parser/tests.h
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/testing.h
#	tools/llama-bench/llama-bench.cpp

tools/mtmd/models/conformer.cpp

@@ -12,7 +12,6 @@ ggml_cgraph * clip_graph_conformer::build() {
     ggml_build_forward_expand(gf, pos_emb);
 
     ggml_tensor * inp = build_inp_raw(1);
-    cb(inp, "input", -1);
 
     auto * cur = ggml_cont(ctx0, ggml_transpose(ctx0, inp));
 

tools/server/server-context.cpp

@@ -864,9 +864,10 @@ private:
         };
 
         // print sample chat example to make it clear which template is used
-        LOG_INF("%s: chat template, chat_template: %s, example_format: '%s'\n", __func__,
-            common_chat_templates_source(chat_templates.get()),
-            common_chat_format_example(chat_templates.get(), params_base.use_jinja, params_base.default_template_kwargs).c_str());
+        // @ngxson modern templates are too long, spam the logs; printing the example is enough
+        LOG_INF("%s: chat template, example_format: '%s'\n", __func__,
+        //      common_chat_templates_source(chat_templates.get()),
+                common_chat_format_example(chat_templates.get(), params_base.use_jinja, params_base.default_template_kwargs).c_str());
 
         if (!is_resume) {
             return init();