feat(llama-cpp): serve Qwen3-TTS through the llama.cpp backend

backend/cpp/bonsai/Makefile

@@ -42,6 +42,7 @@ define bonsai-build
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build purge
 	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
+	bash $(LLAMA_CPP_DIR)/disable-tts-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:$(1)$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build llama.cpp
@@ -79,6 +80,7 @@ bonsai-cpu-all:
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build purge
 	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
+	bash $(LLAMA_CPP_DIR)/disable-tts-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:cpu-all-variants$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build llama.cpp

backend/cpp/llama-cpp/CMakeLists.txt

@@ -115,4 +115,9 @@ if(LLAMA_GRPC_BUILD_TESTS)
     target_include_directories(passthrough_options_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
     target_compile_features(passthrough_options_test PRIVATE cxx_std_17)
     add_test(NAME passthrough_options_test COMMAND passthrough_options_test)
+
+    add_executable(tts_request_options_test tts_request_options_test.cpp tts_request_options.h)
+    target_include_directories(tts_request_options_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
+    target_compile_features(tts_request_options_test PRIVATE cxx_std_17)
+    add_test(NAME tts_request_options_test COMMAND tts_request_options_test)
 endif()

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=221f0f6356efe2260023208365705ec5d5a7c8f5
+LLAMA_VERSION?=9de0fcf2b3e587a43f293d9a2b6ec0a32991f768
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/disable-tts-task.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+# Mark a copied gRPC server as targeting a llama.cpp fork that does not carry
+# LocalAI's SERVER_TASK_TYPE_TTS patch. The RPCs remain present in the shared
+# protobuf service, but respond with UNIMPLEMENTED instead of referencing
+# server task types and mtmd gen-audio APIs absent from those forks.
+
+set -euo pipefail
+
+if [[ $# -ne 1 ]]; then
+    echo "usage: $0 <grpc-server.cpp>" >&2
+    exit 2
+fi
+
+SRC=$1
+
+if [[ ! -f "$SRC" ]]; then
+    echo "grpc-server.cpp not found at $SRC" >&2
+    exit 2
+fi
+
+if grep -q '^#define LOCALAI_LLAMA_CPP_NO_TTS_TASK' "$SRC"; then
+    echo "==> $SRC already disables the LocalAI TTS task, skipping"
+    exit 0
+fi
+
+awk '
+    !done && /^#include/ {
+        print "#define LOCALAI_LLAMA_CPP_NO_TTS_TASK 1"
+        print "// ^ injected by disable-tts-task.sh for an unpatched llama.cpp fork"
+        print ""
+        done = 1
+    }
+    { print }
+    END {
+        if (!done) {
+            print "disable-tts-task.sh: no #include anchor found" > "/dev/stderr"
+            exit 1
+        }
+    }
+' "$SRC" > "$SRC.tmp"
+mv "$SRC.tmp" "$SRC"
+
+echo "==> LocalAI TTS task disabled in $SRC"