Add tool call to hot topics

Author: ochafik

README.md

@@ -18,6 +18,7 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
 
 - **How to use [MTLResidencySet](https://developer.apple.com/documentation/metal/mtlresidencyset?language=objc) to keep the GPU memory active?** https://github.com/ggerganov/llama.cpp/pull/11427
 - **VS Code extension for FIM completions:** https://github.com/ggml-org/llama.vscode
+- Universal tool call support in `llama-server`: https://github.com/ggerganov/llama.cpp/pull/9639
 - Vim/Neovim plugin for FIM completions: https://github.com/ggml-org/llama.vim
 - Introducing GGUF-my-LoRA https://github.com/ggerganov/llama.cpp/discussions/10123
 - Hugging Face Inference Endpoints now support GGUF out of the box! https://github.com/ggerganov/llama.cpp/discussions/9669

tests/test-chat.cpp

@@ -3,8 +3,7 @@
 //  Also acts as a CLI to generate a Markdown summary of the formats of Jinja templates,
 //  e.g. given Minja (http://github.com/google/minja) checked out in parent dir:
 //
-//    cmake -B build && cmake --build build --parallel && \
-//      ./build/bin/test-chat ../minja/build/tests/*.jinja 2>/dev/null
+//    cmake -B build && cmake --build build --parallel && ./build/bin/test-chat ../minja/build/tests/*.jinja 2>/dev/null
 //
 #include "chat.hpp"
 #include "chat-template.hpp"