Merge pull request #1013 from kvcache-ai/work-concurrent

In v0.2.4 version, we’ve added highly desired multi-concurrency support to the community through a major refactor of the whole architecture.

csrc/balance_serve/sched/CMakeLists.txt

+set(CMAKE_CXX_FLAGS "-Og -march=native -Wall -Wextra -g -fPIC")
+# set(CMAKE_CXX_FLAGS "-O3 -march=native -Wall -Wextra -fPIC")
+
+set(UTILS_DIR ${CMAKE_CURRENT_SOURCE_DIR}/utils)
+
+add_library(sched_metrics metrics.cpp)
+target_include_directories(sched_metrics PRIVATE ${UTILS_DIR})
+target_link_libraries(sched_metrics PUBLIC prometheus-cpp::pull)
+
+
+add_library(sched scheduler.cpp)
+target_include_directories(sched PRIVATE ${SPDLOG_DIR}/include ${FMT_DIR}/include ${UTILS_DIR} ${KVC2_INCLUDE_DIR})
+target_link_libraries(sched PUBLIC pthread ${TORCH_LIBRARIES} kvc2 async_store sched_metrics)
+
+pybind11_add_module(sched_ext bind.cpp)
+target_link_libraries(sched_ext PUBLIC sched ${TORCH_LIBRARIES} ${TORCH_PYTHON_LIBRARY})
+
+
+