ci : add model tests + script wrapper (#4586)

* scripts : add lib.sh and lib_test.sh

* scripts : stub out new ci-run.sh script

* scripts : switch to PascalCase for functions

This looks a little odd at first, but I find it very useful as a
convention to know if a command is part of our code vs a builtin.

* scripts : add some fancy conversion from snake_case to PascalCase

* Add venv to ci/run.sh

* Revert scripts work

* scripts : add wrapper script for local use of ci/run.sh

* Simplify .gitignore for tests, clang-tidy fixes

* Label all ctest tests

* ci : ctest uses -L main

* Attempt at writing ctest_with_model

* Update test-model-load-cancel

* ci : add ctest_with_model for debug and release

ggml-ci

* Fix gg_get_model function

ggml-ci

* got stuck on CMake

* Add get_model.cpp to tests/CMakeLists.txt

ggml-ci

* Fix README.md output for ctest_with_model

ggml-ci

* workflows : use `-L main` for all ctest

ggml-ci

* Fixes

* GG_RUN_CTEST_MODELFILE => LLAMACPP_TESTMODELFILE
* Always show warning rather than failing if model file variable is not
  set

* scripts : update usage text for ci-run.sh

6 files changed, 67 insertions, 11 deletions

diff --git a/tests/.gitignore b/tests/.gitignore
new file mode 100644
index 00000000..59be43b9
--- /dev/null
+++ b/tests/.gitignore
@@ -0,0 +1,2 @@
+*
+!*.*
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
index d7aaab84..3e40a78c 100644
--- a/tests/CMakeLists.txt
+++ b/tests/CMakeLists.txt
@@ -1,6 +1,6 @@
 function(llama_build_executable source)
     get_filename_component(TEST_TARGET ${source} NAME_WE)
-    add_executable(${TEST_TARGET} ${source})
+    add_executable(${TEST_TARGET} ${source} get-model.cpp)
     install(TARGETS ${TEST_TARGET} RUNTIME)
     target_link_libraries(${TEST_TARGET} PRIVATE common)
 endfunction()
@@ -8,14 +8,20 @@ endfunction()
 function(llama_test_executable name source)
     get_filename_component(TEST_TARGET ${source} NAME_WE)
     add_test(NAME ${name} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
+    set_property(TEST ${name} PROPERTY LABELS "main")
 endfunction()
 
 function(llama_build_and_test_executable source)
+    llama_build_and_test_executable_with_label(${source} "main")
+endfunction()
+
+function(llama_build_and_test_executable_with_label source label)
     get_filename_component(TEST_TARGET ${source} NAME_WE)
-    add_executable(${TEST_TARGET} ${source})
+    add_executable(${TEST_TARGET} ${source} get-model.cpp)
     install(TARGETS ${TEST_TARGET} RUNTIME)
     target_link_libraries(${TEST_TARGET} PRIVATE common)
     add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
+    set_property(TEST ${TEST_TARGET} PROPERTY LABELS ${label})
 endfunction()
 
 # llama_build_and_test_executable(test-double-float.cpp) # SLOW
@@ -49,10 +55,12 @@ llama_build_and_test_executable(test-llama-grammar.cpp)
 llama_build_and_test_executable(test-grad0.cpp)
 # llama_build_and_test_executable(test-opt.cpp) # SLOW
 llama_build_and_test_executable(test-backend-ops.cpp)
-llama_build_and_test_executable(test-autorelease.cpp)
 
 llama_build_and_test_executable(test-rope.cpp)
 
+llama_build_and_test_executable_with_label(test-model-load-cancel.cpp "model")
+llama_build_and_test_executable_with_label(test-autorelease.cpp "model")
+
 # dummy executable - not installed
 get_filename_component(TEST_TARGET test-c.c NAME_WE)
 add_executable(${TEST_TARGET} test-c.c)
diff --git a/tests/get-model.cpp b/tests/get-model.cpp
new file mode 100644
index 00000000..4edb685f
--- /dev/null
+++ b/tests/get-model.cpp
@@ -0,0 +1,21 @@
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+
+#include "get-model.h"
+
+char * get_model_or_exit(int argc, char *argv[]) {
+    char * model_path;
+    if (argc > 1) {
+        model_path = argv[1];
+
+    } else {
+        model_path = getenv("LLAMACPP_TEST_MODELFILE");
+        if (!model_path || strlen(model_path) == 0) {
+            fprintf(stderr, "\033[33mWARNING: No model file provided. Skipping this test. Set LLAMACPP_TEST_MODELFILE=<gguf_model_path> to silence this warning and run this test.\n\033[0m");
+            exit(EXIT_SUCCESS);
+        }
+    }
+
+    return model_path;
+}
diff --git a/tests/get-model.h b/tests/get-model.h
new file mode 100644
index 00000000..81a3a0fe
--- /dev/null
+++ b/tests/get-model.h
@@ -0,0 +1,2 @@
+#pragma once
+char * get_model_or_exit(int, char*[]);
diff --git a/tests/test-autorelease.cpp b/tests/test-autorelease.cpp
index 289c6ba6..36a23c0b 100644
--- a/tests/test-autorelease.cpp
+++ b/tests/test-autorelease.cpp
@@ -5,19 +5,15 @@
 #include <thread>
 
 #include "llama.h"
+#include "get-model.h"
 
 // This creates a new context inside a pthread and then tries to exit cleanly.
 int main(int argc, char ** argv) {
-    if (argc < 2) {
-        printf("Usage: %s model.gguf\n", argv[0]);
-        return 0; // intentionally return success
-    }
+    auto * model_path = get_model_or_exit(argc, argv);
 
-    const std::string fname = argv[1];
-
-    std::thread([&fname]() {
+    std::thread([&model_path]() {
         llama_backend_init(false);
-        auto * model = llama_load_model_from_file(fname.c_str(), llama_model_default_params());
+        auto * model = llama_load_model_from_file(model_path, llama_model_default_params());
         auto * ctx = llama_new_context_with_model(model, llama_context_default_params());
         llama_free(ctx);
         llama_free_model(model);
diff --git a/tests/test-model-load-cancel.cpp b/tests/test-model-load-cancel.cpp
new file mode 100644
index 00000000..7ea4bbac
--- /dev/null
+++ b/tests/test-model-load-cancel.cpp
@@ -0,0 +1,27 @@
+#include "llama.h"
+#include "get-model.h"
+
+#include <cstdlib>
+
+int main(int argc, char *argv[] ) {
+    auto * model_path = get_model_or_exit(argc, argv);
+    auto * file = fopen(model_path, "r");
+    if (file == nullptr) {
+        fprintf(stderr, "no model at '%s' found\n", model_path);
+        return EXIT_FAILURE;
+    }
+
+    fprintf(stderr, "using '%s'\n", model_path);
+    fclose(file);
+
+    llama_backend_init(false);
+    auto params = llama_model_params{};
+    params.use_mmap = false;
+    params.progress_callback = [](float progress, void * ctx){
+        (void) ctx;
+        return progress > 0.50;
+    };
+    auto * model = llama_load_model_from_file(model_path, params);
+    llama_backend_free();
+    return model == nullptr ? EXIT_SUCCESS : EXIT_FAILURE;
+}