make: Use ccache for faster compilation (#5318)

* make: Use ccache for faster compilation

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 8c04e4c19c5d7870219e9726bd0298a87cb66a95..427015be52f693e5fb1d2c1d8e39fac8c69e5642 100644 (file)
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -809,9 +809,9 @@ if (LLAMA_CCACHE)
     if (LLAMA_CCACHE_FOUND)
         set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
         set(ENV{CCACHE_SLOPPINESS} time_macros)
-        message(STATUS "Using ccache")
+        message(STATUS "ccache found, compilation results will be cached. Disable with LLAMA_CCACHE=OFF.")
     else()
-        message(STATUS "Warning: ccache not found - consider installing it or use LLAMA_CCACHE=OFF")
+        message(STATUS "Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF")
     endif ()
 endif()
 

diff --git a/Makefile b/Makefile
index 21d5e15baa764cecd238aa2f7cf1f40dd37fc803..ba73f063709c7094cb9cc8a6826236ed01b41bc9 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -112,6 +112,18 @@ MK_CXXFLAGS   += -O3
 MK_NVCCFLAGS  += -O3
 endif
 
+ifndef LLAMA_NO_CCACHE
+CCACHE := $(shell which ccache)
+ifdef CCACHE
+export CCACHE_SLOPPINESS = time_macros
+$(info I ccache found, compilation results will be cached. Disable with LLAMA_NO_CCACHE.)
+CC    := $(CCACHE) $(CC)
+CXX   := $(CCACHE) $(CXX)
+else
+$(info I ccache not found. Consider installing it for faster compilation.)
+endif # CCACHE
+endif # LLAMA_NO_CCACHE
+
 # clock_gettime came in POSIX.1b (1993)
 # CLOCK_MONOTONIC came in POSIX.1-2001 / SUSv3 as optional
 # posix_memalign came in POSIX.1-2001 / SUSv3
@@ -374,9 +386,9 @@ ifdef LLAMA_DEBUG
        MK_NVCCFLAGS += -lineinfo
 endif # LLAMA_DEBUG
 ifdef LLAMA_CUDA_NVCC
-       NVCC = $(LLAMA_CUDA_NVCC)
+       NVCC = $(CCACHE) $(LLAMA_CUDA_NVCC)
 else
-       NVCC = nvcc
+       NVCC = $(CCACHE) nvcc
 endif #LLAMA_CUDA_NVCC
 ifdef CUDA_DOCKER_ARCH
        MK_NVCCFLAGS += -Wno-deprecated-gpu-targets -arch=$(CUDA_DOCKER_ARCH)
@@ -483,7 +495,7 @@ ifdef LLAMA_HIPBLAS
                ROCM_PATH       ?= /opt/rocm
                GPU_TARGETS ?= $(shell $(ROCM_PATH)/llvm/bin/amdgpu-arch)
        endif
-       HIPCC                   ?= $(ROCM_PATH)/bin/hipcc
+       HIPCC                   ?= $(CCACHE) $(ROCM_PATH)/bin/hipcc
        LLAMA_CUDA_DMMV_X       ?= 32
        LLAMA_CUDA_MMV_Y        ?= 1
        LLAMA_CUDA_KQUANTS_ITER ?= 2
@@ -607,97 +619,135 @@ libllama.a: llama.o ggml.o $(OBJS) $(COMMON_DEPS)
 
 clean:
        rm -vrf *.o tests/*.o *.so *.a *.dll benchmark-matmult common/build-info.cpp *.dot $(COV_TARGETS) $(BUILD_TARGETS) $(TEST_TARGETS)
+       find examples pocs -type f -name "*.o" -delete
 
 #
 # Examples
 #
 
+# $< is the first prerequisite, i.e. the source file.
+# Explicitly compile this to an object file so that it can be cached with ccache.
+# The source file is then filtered out from $^ (the list of all prerequisites) and the object file is added instead.
+
+# Helper function that replaces .c, .cpp, and .cu file endings with .o:
+GET_OBJ_FILE = $(patsubst %.c,%.o,$(patsubst %.cpp,%.o,$(patsubst %.cu,%.o,$(1))))
+
 main: examples/main/main.cpp                                  ggml.o llama.o $(COMMON_DEPS) console.o grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
        @echo
        @echo '====  Run ./main -h for help.  ===='
        @echo
 
 infill: examples/infill/infill.cpp                            ggml.o llama.o $(COMMON_DEPS) console.o grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 simple: examples/simple/simple.cpp                            ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tokenize: examples/tokenize/tokenize.cpp                      ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 batched: examples/batched/batched.cpp                         ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 batched-bench: examples/batched-bench/batched-bench.cpp       build-info.o ggml.o llama.o common.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 quantize: examples/quantize/quantize.cpp                      build-info.o ggml.o llama.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 quantize-stats: examples/quantize-stats/quantize-stats.cpp    build-info.o ggml.o llama.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 perplexity: examples/perplexity/perplexity.cpp                ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 imatrix: examples/imatrix/imatrix.cpp                         ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 embedding: examples/embedding/embedding.cpp                   ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 save-load-state: examples/save-load-state/save-load-state.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 server: examples/server/server.cpp examples/server/oai.hpp examples/server/utils.hpp examples/server/httplib.h examples/server/json.hpp examples/server/index.html.hpp examples/server/index.js.hpp examples/server/completion.js.hpp examples/llava/clip.cpp examples/llava/clip.h common/stb_image.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS) $(LWINSOCK2) -Wno-cast-qual
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) -c examples/llava/clip.cpp -o $(call GET_OBJ_FILE, examples/llava/clip.cpp) -Wno-cast-qual
+       $(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h %.hpp $< examples/llava/clip.cpp,$^) $(call GET_OBJ_FILE, $<) $(call GET_OBJ_FILE, examples/llava/clip.cpp) -o $@ $(LDFLAGS) $(LWINSOCK2)
 
 gguf: examples/gguf/gguf.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 convert-llama2c-to-ggml: examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp ggml.o llama.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 llama-bench: examples/llama-bench/llama-bench.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 libllava.a: examples/llava/llava.cpp examples/llava/llava.h examples/llava/clip.cpp examples/llava/clip.h common/stb_image.h common/base64.hpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
        $(CXX) $(CXXFLAGS) -static -fPIC -c $< -o $@ -Wno-cast-qual
 
 llava-cli: examples/llava/llava-cli.cpp examples/llava/clip.h examples/llava/clip.cpp examples/llava/llava.h examples/llava/llava.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS) -Wno-cast-qual
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) -c examples/llava/clip.cpp  -o $(call GET_OBJ_FILE, examples/llava/clip.cpp) -Wno-cast-qual
+       $(CXX) $(CXXFLAGS) -c examples/llava/llava.cpp -o $(call GET_OBJ_FILE, examples/llava/llava.cpp)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $< examples/llava/clip.cpp examples/llava/llava.cpp,$^) $(call GET_OBJ_FILE, $<) $(call GET_OBJ_FILE, examples/llava/clip.cpp) $(call GET_OBJ_FILE, examples/llava/llava.cpp) -o $@ $(LDFLAGS)
 
 baby-llama: examples/baby-llama/baby-llama.cpp ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 beam-search: examples/beam-search/beam-search.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 finetune: examples/finetune/finetune.cpp ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 export-lora: examples/export-lora/export-lora.cpp ggml.o common/common.h $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 speculative: examples/speculative/speculative.cpp ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 parallel: examples/parallel/parallel.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 lookahead: examples/lookahead/lookahead.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 lookup: examples/lookup/lookup.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 passkey: examples/passkey/passkey.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 ifeq ($(UNAME_S),Darwin)
 swift: examples/batched.swift
@@ -705,7 +755,7 @@ swift: examples/batched.swift
 endif
 
 common/build-info.cpp: $(wildcard .git/index) scripts/build-info.sh
-       @sh scripts/build-info.sh $(CC) > $@.tmp
+       @sh scripts/build-info.sh "$(CC)" > $@.tmp
        @if ! cmp -s $@.tmp $@; then \
                mv $@.tmp $@; \
        else \
@@ -722,7 +772,8 @@ build-info.o: common/build-info.cpp
 tests: $(TEST_TARGETS)
 
 benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.o ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 run-benchmark-matmult: benchmark-matmult
        ./$@
@@ -730,58 +781,76 @@ run-benchmark-matmult: benchmark-matmult
 .PHONY: run-benchmark-matmult swift
 
 vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 q8dot: pocs/vdot/q8dot.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-llama-grammar: tests/test-llama-grammar.cpp ggml.o grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-grammar-parser: tests/test-grammar-parser.cpp ggml.o llama.o grammar-parser.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-double-float: tests/test-double-float.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-grad0: tests/test-grad0.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-opt: tests/test-opt.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-quantize-fns: tests/test-quantize-fns.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-quantize-perf: tests/test-quantize-perf.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-sampling: tests/test-sampling.cpp ggml.o llama.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-tokenizer-0-falcon: tests/test-tokenizer-0-falcon.cpp ggml.o llama.o $(COMMON_DEPS) console.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-tokenizer-0-llama: tests/test-tokenizer-0-llama.cpp ggml.o llama.o $(COMMON_DEPS) console.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-tokenizer-1-bpe: tests/test-tokenizer-1-bpe.cpp ggml.o llama.o $(COMMON_DEPS) console.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-tokenizer-1-llama: tests/test-tokenizer-1-llama.cpp ggml.o llama.o $(COMMON_DEPS) console.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-rope: tests/test-rope.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-c.o: tests/test-c.c llama.h
        $(CC) $(CFLAGS) -c $(filter-out %.h,$^) -o $@
 
 tests/test-backend-ops: tests/test-backend-ops.cpp ggml.o $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-model-load-cancel: tests/test-model-load-cancel.cpp ggml.o llama.o tests/get-model.cpp $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
 tests/test-autorelease: tests/test-autorelease.cpp ggml.o llama.o tests/get-model.cpp $(COMMON_DEPS) $(OBJS)
-       $(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+       $(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+       $(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)