Files
mudler's LocalAI [bot] 4c4911fe2c chore: ⬆️ Update ggml-org/llama.cpp to 0021a77de0a8966059dc94548fb3b96654e0bb12 (#11508)
* chore(llama-cpp): update upstream revision

Assisted-by: Codex:gpt-5.6

* fix(llama-cpp): refresh server patch contexts

The new llama.cpp pin changed the slot reset and prompt batch code. GNU patch accepted stale hunks with fuzz, which left the L4T build with invalid source.

Refresh both server patches against the pinned source so each hunk applies at its intended location.

Assisted-by: Codex:gpt-5

* fix(llama-cpp): adapt metrics result fields

The updated llama.cpp groups cumulative counters under server_metrics. Probe the result layout so the shared adapter also compiles against older forks.

Assisted-by: Codex:gpt-5

* fix(llama-cpp): refresh TTS patch offsets

GNU patch rejects the stale pre-decode hunk after the score patch changes the same file. Anchor the TTS hunks to the pinned llama.cpp source so the full series applies without fuzz.

Assisted-by: Codex:gpt-5.4

* fix(llama-cpp): normalize batch threads

The updated llama.cpp creates its batch threadpool during model initialization, before the context-level fallback can replace the -1 sentinel. Resolve that sentinel from the inference thread count so model loading does not overflow the threadpool allocation.\n\nAssisted-by: Codex:gpt-5.4

---------

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
2026-08-18 09:45:56 +02:00

129 lines
5.9 KiB
CMake

set(TARGET grpc-server)
set(CMAKE_CXX_STANDARD 17)
cmake_minimum_required(VERSION 3.15)
set(TARGET grpc-server)
set(_PROTOBUF_LIBPROTOBUF libprotobuf)
set(_REFLECTION grpc++_reflection)
if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
# Set correct Homebrew install folder for Apple Silicon and Intel Macs
if (CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
set(HOMEBREW_DEFAULT_PREFIX "/opt/homebrew")
else()
set(HOMEBREW_DEFAULT_PREFIX "/usr/local")
endif()
link_directories("${HOMEBREW_DEFAULT_PREFIX}/lib")
include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
endif()
find_package(absl CONFIG REQUIRED)
find_package(Protobuf CONFIG REQUIRED)
find_package(gRPC CONFIG REQUIRED)
find_program(_PROTOBUF_PROTOC protoc)
set(_GRPC_GRPCPP grpc++)
find_program(_GRPC_CPP_PLUGIN_EXECUTABLE grpc_cpp_plugin)
include_directories(${CMAKE_CURRENT_BINARY_DIR})
include_directories(${Protobuf_INCLUDE_DIRS})
message(STATUS "Using protobuf version ${Protobuf_VERSION} | Protobuf_INCLUDE_DIRS: ${Protobuf_INCLUDE_DIRS} | CMAKE_CURRENT_BINARY_DIR: ${CMAKE_CURRENT_BINARY_DIR}")
# Proto file
get_filename_component(hw_proto "../../../../../../backend/backend.proto" ABSOLUTE)
get_filename_component(hw_proto_path "${hw_proto}" PATH)
# Generated sources
set(hw_proto_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
set(hw_proto_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
set(hw_grpc_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
set(hw_grpc_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
add_custom_command(
OUTPUT "${hw_proto_srcs}" "${hw_proto_hdrs}" "${hw_grpc_srcs}" "${hw_grpc_hdrs}"
COMMAND ${_PROTOBUF_PROTOC}
ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
--cpp_out "${CMAKE_CURRENT_BINARY_DIR}"
-I "${hw_proto_path}"
--plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN_EXECUTABLE}"
"${hw_proto}"
DEPENDS "${hw_proto}")
# hw_grpc_proto: force STATIC. Under the CPU_ALL_VARIANTS build BUILD_SHARED_LIBS=ON
# (ggml/llama become shared), which would otherwise make this glue library a DSO. As a
# DSO it references the hidden-visibility symbols in the static libprotobuf.a, which the
# linker cannot satisfy ("hidden symbol ... in libprotobuf.a is referenced by DSO").
# Keeping it STATIC links protobuf/gRPC directly into the grpc-server executable while
# only ggml/llama stay shared. No effect on the static variants (already BUILD_SHARED_LIBS=OFF).
add_library(hw_grpc_proto STATIC
${hw_grpc_srcs}
${hw_grpc_hdrs}
${hw_proto_srcs}
${hw_proto_hdrs} )
add_executable(${TARGET} grpc-server.cpp json.hpp httplib.h)
target_include_directories(${TARGET} PRIVATE ../llava)
target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
# Upstream llama.cpp renamed the `common` helpers library to `llama-common`.
# Forks that branched before the rename (e.g. llama-cpp-turboquant) still
# expose it as `common`. Detect which one is present so the same CMakeLists
# drives both builds — otherwise an unresolved name silently degrades to a
# plain `-l` flag and the PUBLIC include dir (where common.h lives) is lost.
if (TARGET llama-common)
set(_LLAMA_COMMON_TARGET llama-common)
else()
set(_LLAMA_COMMON_TARGET common)
endif()
target_link_libraries(${TARGET} PRIVATE ${_LLAMA_COMMON_TARGET} llama mtmd ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
absl::flags_parse
gRPC::${_REFLECTION}
gRPC::${_GRPC_GRPCPP}
protobuf::${_PROTOBUF_LIBPROTOBUF})
target_compile_features(${TARGET} PRIVATE cxx_std_11)
if(TARGET BUILD_INFO)
add_dependencies(${TARGET} BUILD_INFO)
endif()
# Unit test for the message-content normalization helper (message_content.h).
# Off by default so the normal backend build is untouched; enable with
# -DLLAMA_GRPC_BUILD_TESTS=ON and run via ctest. It reuses llama.cpp's vendored
# <nlohmann/json.hpp> (propagated by the common helpers library) so it has no
# extra dependency beyond what the backend already builds against.
option(LLAMA_GRPC_BUILD_TESTS "Build grpc-server unit tests" OFF)
if(LLAMA_GRPC_BUILD_TESTS)
enable_testing()
add_executable(message_content_test message_content_test.cpp message_content.h)
target_include_directories(message_content_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
target_link_libraries(message_content_test PRIVATE ${_LLAMA_COMMON_TARGET})
target_compile_features(message_content_test PRIVATE cxx_std_17)
add_test(NAME message_content_test COMMAND message_content_test)
# Parent-death watcher test (parent_watch.h) — standard library only, but
# needs a threading runtime for std::thread.
find_package(Threads REQUIRED)
add_executable(parent_watch_test parent_watch_test.cpp parent_watch.h)
target_include_directories(parent_watch_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
target_link_libraries(parent_watch_test PRIVATE Threads::Threads)
target_compile_features(parent_watch_test PRIVATE cxx_std_17)
add_test(NAME parent_watch_test COMMAND parent_watch_test)
add_executable(passthrough_options_test passthrough_options_test.cpp passthrough_options.h)
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)
add_executable(thread_params_test thread_params_test.cpp thread_params.h)
target_include_directories(thread_params_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
target_compile_features(thread_params_test PRIVATE cxx_std_17)
add_test(NAME thread_params_test COMMAND thread_params_test)
endif()