Add git-based build information for better issue tracking (#1232)

* Add git-based build information for better issue tracking

* macOS fix

* "build (hash)" and "CMAKE_SOURCE_DIR" changes

* Redo "CMAKE_CURRENT_SOURCE_DIR" and clearer build messages

* Fix conditional dependency on missing target

* Broke out build-info.cmake, added find_package fallback, and added build into to all examples, added dependencies to Makefile

* 4 space indenting for cmake, attempt to clean up my mess in Makefile

* Short hash, less fancy Makefile, and don't modify build-info.h if it wouldn't change it

18 files changed, 185 insertions, 21 deletions

diff --git a/.gitignore b/.gitignore
index 565866f..e479c61 100644
--- a/.gitignore
+++ b/.gitignore
@@ -32,6 +32,7 @@ models/*
 /vdot
 /Pipfile
 
+build-info.h
 arm_neon.h
 compile_commands.json
 
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 0983061..f6a66da 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -73,6 +73,41 @@ option(LLAMA_BUILD_TESTS            "llama: build tests"    ${LLAMA_STANDALONE})
 option(LLAMA_BUILD_EXAMPLES         "llama: build examples" ${LLAMA_STANDALONE})
 
 #
+# Build info header
+#
+
+# Write header template to binary dir to keep source directory clean
+file(WRITE "${CMAKE_BINARY_DIR}/BUILD_INFO.h.in" "\
+#ifndef BUILD_INFO_H\n\
+#define BUILD_INFO_H\n\
+\n\
+#define BUILD_NUMBER @BUILD_NUMBER@\n\
+#define BUILD_COMMIT \"@BUILD_COMMIT@\"\n\
+\n\
+#endif // BUILD_INFO_H\n\
+")
+
+# Generate initial build-info.h
+include(${CMAKE_CURRENT_SOURCE_DIR}/scripts/build-info.cmake)
+
+if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
+    # Add a custom target for build-info.h
+    add_custom_target(BUILD_INFO ALL DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/build-info.h")
+
+    # Add a custom command to rebuild build-info.h when .git/index changes
+    add_custom_command(
+        OUTPUT "${CMAKE_CURRENT_SOURCE_DIR}/build-info.h"
+        COMMENT "Generating build details from Git"
+        COMMAND ${CMAKE_COMMAND} -P "${CMAKE_CURRENT_SOURCE_DIR}/scripts/build-info.cmake"
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/.git/index"
+        VERBATIM
+    )
+else()
+    message(WARNING "Git repository not found; to enable automatic generation of build info, make sure Git is installed and the project is a Git repository.")
+endif()
+
+#
 # Compile flags
 #
 
diff --git a/Makefile b/Makefile
index 1d62a44..6ebc3c5 100644
--- a/Makefile
+++ b/Makefile
@@ -181,41 +181,56 @@ llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama-util.h
 common.o: examples/common.cpp examples/common.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
+libllama.so: llama.o ggml.o $(OBJS)
+	$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
+
 clean:
-	rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult
+	rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state build-info.h
 
-main: examples/main/main.cpp ggml.o llama.o common.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+#
+# Examples
+#
+
+main: examples/main/main.cpp build-info.h ggml.o llama.o common.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 	@echo
 	@echo '====  Run ./main -h for help.  ===='
 	@echo
 
-quantize: examples/quantize/quantize.cpp ggml.o llama.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+quantize: examples/quantize/quantize.cpp build-info.h ggml.o llama.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
-quantize-stats: examples/quantize-stats/quantize-stats.cpp ggml.o llama.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o llama.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
-perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o llama.o common.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
-embedding: examples/embedding/embedding.cpp ggml.o llama.o common.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o common.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
-vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o common.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
-libllama.so: llama.o ggml.o $(OBJS)
-	$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
+build-info.h: $(wildcard .git/index) scripts/build-info.sh
+	@scripts/build-info.sh > $@.tmp
+	@if ! cmp -s $@.tmp $@; then \
+		mv $@.tmp $@; \
+	else \
+		rm $@.tmp; \
+	fi
 
 #
 # Tests
 #
 
-benchmark-matmult: examples/benchmark/benchmark-matmult.cpp ggml.o $(OBJS)
-	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 	./$@
 
+vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+
 .PHONY: tests
 tests:
 	bash ./tests/run-tests.sh
diff --git a/examples/benchmark/CMakeLists.txt b/examples/benchmark/CMakeLists.txt
index 05deebc..0376961 100644
--- a/examples/benchmark/CMakeLists.txt
+++ b/examples/benchmark/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET benchmark)
 add_executable(${TARGET} benchmark-matmult.cpp)
 target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/benchmark/benchmark-matmult.cpp b/examples/benchmark/benchmark-matmult.cpp
index 19cbab1..2cc1a14 100644
--- a/examples/benchmark/benchmark-matmult.cpp
+++ b/examples/benchmark/benchmark-matmult.cpp
@@ -1,5 +1,6 @@
 #include <locale.h>
 #include "ggml.h"
+#include "build-info.h"
 #include <assert.h>
 #include <math.h>
 #include <cstring>
@@ -90,9 +91,10 @@ int main(int argc, char ** argv)  {
         }
     }
 
-    // create the ggml context
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
     printf("Starting Test\n");
 
+    // create the ggml context
     struct ggml_context * ctx;
     //const int sizex = 4096;
     //const int sizey = 11008;
diff --git a/examples/embedding/CMakeLists.txt b/examples/embedding/CMakeLists.txt
index 88c425d..db73b6b 100644
--- a/examples/embedding/CMakeLists.txt
+++ b/examples/embedding/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET embedding)
 add_executable(${TARGET} embedding.cpp)
 target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp
index e10de61..b3e0014 100644
--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@@ -1,5 +1,6 @@
 #include "common.h"
 #include "llama.h"
+#include "build-info.h"
 
 #include <ctime>
 
@@ -18,11 +19,13 @@ int main(int argc, char ** argv) {
                 "expect poor results\n", __func__, params.n_ctx);
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     if (params.seed <= 0) {
         params.seed = time(NULL);
     }
 
-    fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
+    fprintf(stderr, "%s: seed  = %d\n", __func__, params.seed);
 
     std::mt19937 rng(params.seed);
     if (params.random_prompt) {
diff --git a/examples/main/CMakeLists.txt b/examples/main/CMakeLists.txt
index b2dcc29..c364242 100644
--- a/examples/main/CMakeLists.txt
+++ b/examples/main/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET main)
 add_executable(${TARGET} main.cpp)
 target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/main/main.cpp b/examples/main/main.cpp
index 78fc9a1..7dc1005 100644
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@@ -5,6 +5,7 @@
 
 #include "common.h"
 #include "llama.h"
+#include "build-info.h"
 
 #include <cassert>
 #include <cinttypes>
@@ -81,11 +82,13 @@ int main(int argc, char ** argv) {
                 "expect poor results\n", __func__, params.n_ctx);
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     if (params.seed <= 0) {
         params.seed = time(NULL);
     }
 
-    fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
+    fprintf(stderr, "%s: seed  = %d\n", __func__, params.seed);
 
     std::mt19937 rng(params.seed);
     if (params.random_prompt) {
diff --git a/examples/perplexity/CMakeLists.txt b/examples/perplexity/CMakeLists.txt
index 5836df8..61b17b8 100644
--- a/examples/perplexity/CMakeLists.txt
+++ b/examples/perplexity/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET perplexity)
 add_executable(${TARGET} perplexity.cpp)
 target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp
index 615157e..2ca3388 100644
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@@ -1,5 +1,6 @@
 #include "common.h"
 #include "llama.h"
+#include "build-info.h"
 
 #include <cmath>
 #include <ctime>
@@ -106,11 +107,13 @@ int main(int argc, char ** argv) {
                 "expect poor results\n", __func__, params.n_ctx);
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     if (params.seed <= 0) {
         params.seed = time(NULL);
     }
 
-    fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
+    fprintf(stderr, "%s: seed  = %d\n", __func__, params.seed);
 
     std::mt19937 rng(params.seed);
     if (params.random_prompt) {
diff --git a/examples/quantize-stats/quantize-stats.cpp b/examples/quantize-stats/quantize-stats.cpp
index 4e6c2c8..9a2aa7c 100644
--- a/examples/quantize-stats/quantize-stats.cpp
+++ b/examples/quantize-stats/quantize-stats.cpp
@@ -1,4 +1,5 @@
 #include "ggml.h"
+#include "build-info.h"
 
 #define LLAMA_API_INTERNAL
 #include "llama.h"
@@ -308,6 +309,8 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     // load the model
     fprintf(stderr, "Loading model\n");
 
diff --git a/examples/quantize/CMakeLists.txt b/examples/quantize/CMakeLists.txt
index fb27d45..475fc8b 100644
--- a/examples/quantize/CMakeLists.txt
+++ b/examples/quantize/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET quantize)
 add_executable(${TARGET} quantize.cpp)
 target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
index dd175c6..198bd5f 100644
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@@ -1,5 +1,6 @@
 #include "ggml.h"
 #include "llama.h"
+#include "build-info.h"
 
 #include <cstdio>
 #include <map>
@@ -50,6 +51,8 @@ int main(int argc, char ** argv) {
         ftype = (enum llama_ftype)atoi(argv[3]);
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     int nthread = argc > 4 ? atoi(argv[4]) : 0;
 
     const int64_t t_main_start_us = ggml_time_us();
diff --git a/examples/save-load-state/CMakeLists.txt b/examples/save-load-state/CMakeLists.txt
index cff79fa..08dbe5c 100644
--- a/examples/save-load-state/CMakeLists.txt
+++ b/examples/save-load-state/CMakeLists.txt
@@ -2,3 +2,6 @@ set(TARGET save-load-state)
 add_executable(${TARGET} save-load-state.cpp)
 target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()
diff --git a/examples/save-load-state/save-load-state.cpp b/examples/save-load-state/save-load-state.cpp
index f1531ba..ea0a984 100644
--- a/examples/save-load-state/save-load-state.cpp
+++ b/examples/save-load-state/save-load-state.cpp
@@ -1,5 +1,6 @@
 #include "common.h"
 #include "llama.h"
+#include "build-info.h"
 
 #include <vector>
 #include <cstdio>
@@ -17,6 +18,8 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+    fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
+
     if (params.n_predict < 0) {
         params.n_predict = 16;
     }
diff --git a/scripts/build-info.cmake b/scripts/build-info.cmake
new file mode 100644
index 0000000..fb46ed2
--- /dev/null
+++ b/scripts/build-info.cmake
@@ -0,0 +1,53 @@
+set(TEMPLATE_FILE "${CMAKE_BINARY_DIR}/BUILD_INFO.h.in")
+set(HEADER_FILE "${CMAKE_CURRENT_SOURCE_DIR}/build-info.h")
+set(BUILD_NUMBER 0)
+set(BUILD_COMMIT "unknown")
+
+# Look for git
+find_package(Git)
+if(NOT Git_FOUND)
+    execute_process(
+        COMMAND which git
+        OUTPUT_VARIABLE GIT_EXECUTABLE
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+    )
+    if(NOT GIT_EXECUTABLE STREQUAL "")
+        set(Git_FOUND TRUE)
+        message(STATUS "Found Git using 'which': ${GIT_EXECUTABLE}")
+    else()
+        message(WARNING "Git not found using 'find_package' or 'which'. Build info will not be accurate. Consider installing Git or ensuring it is in the PATH.")
+    endif()
+endif()
+
+# Get the commit count and hash
+if(Git_FOUND)
+    execute_process(
+        COMMAND ${GIT_EXECUTABLE} rev-parse --short HEAD
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        OUTPUT_VARIABLE HEAD
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        RESULT_VARIABLE GIT_HEAD_RESULT
+    )
+    execute_process(
+        COMMAND ${GIT_EXECUTABLE} rev-list --count HEAD
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        OUTPUT_VARIABLE COUNT
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        RESULT_VARIABLE GIT_COUNT_RESULT
+    )
+    if(GIT_HEAD_RESULT EQUAL 0 AND GIT_COUNT_RESULT EQUAL 0)
+        set(BUILD_COMMIT ${HEAD})
+        set(BUILD_NUMBER ${COUNT})
+    endif()
+endif()
+
+# Only write the header if it's changed to prevent unnecessary recompilation
+if(EXISTS ${HEADER_FILE})
+    file(STRINGS ${HEADER_FILE} CONTENTS REGEX "BUILD_COMMIT \"([^\"]*)\"")
+    list(GET CONTENTS 0 EXISTING)
+    if(NOT EXISTING STREQUAL "#define BUILD_COMMIT \"${BUILD_COMMIT}\"")
+        configure_file(${TEMPLATE_FILE} ${HEADER_FILE})
+    endif()
+else()
+    configure_file(${TEMPLATE_FILE} ${HEADER_FILE})
+endif()
diff --git a/scripts/build-info.sh b/scripts/build-info.sh
new file mode 100755
index 0000000..507d7e1
--- /dev/null
+++ b/scripts/build-info.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+
+BUILD_NUMBER="0"
+BUILD_COMMIT="unknown"
+
+REV_LIST=$(git rev-list --count HEAD)
+if [ $? -eq 0 ]; then
+  BUILD_NUMBER=$REV_LIST
+fi
+
+REV_PARSE=$(git rev-parse --short HEAD)
+if [ $? -eq 0 ]; then
+  BUILD_COMMIT=$REV_PARSE
+fi
+
+echo "#ifndef BUILD_INFO_H"
+echo "#define BUILD_INFO_H"
+echo ""
+echo "#define BUILD_NUMBER $BUILD_NUMBER"
+echo "#define BUILD_COMMIT \"$BUILD_COMMIT\""
+echo ""
+echo "#endif // BUILD_INFO_H"